Robust RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

17 papers in the last four weeks, up 467% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 153

Jun 8, 2026cs.RO

CG-MuTra: Continuously-Gated Multi-Terrain Adaptive Recovery for Unified Humanoid Fall Recovery and Locomotion

Falling is an inherent risk for humanoid robots operating in unstructured environments. Existing reinforcement learning methods that leverage expert motion priors are predominantly trained on flat-ground fall-recovery tasks and typically rely on hard switching between separate recovery and locomotion controllers. As a result, such policies struggle to achieve smooth and robust recovery behaviors when deployed on complex terrains such as slopes and gravel. This paper presents \textbf{CG-MuTra}, a unified continuously-gated multi-scale discriminator framework for multi-terrain adaptive fall recovery. CG-MuTra introduces a proprioceptively-derived continuous gate

α= f(z_{\mathrm{root}}, s)

that softly blends three discriminators operating at different temporal horizons: frame-level stability (

Φ_{\mathrm{frame}}

,

H=1

), temporal smoothness (

Φ_{\mathrm{seq}}

,

H=5

), and gait periodicity (

Φ_{\mathrm{gait}}

,

H=10

). This design enables seamless recovery-to-locomotion transitions without explicit mode switching. Furthermore, we propose a Terrain-Pose Risk Coupling Sampler (TPRCS) that explicitly couples dangerous edge initial poses with terrain dynamics during training, forming a closed-loop synergy with the terrain-privileged shaping term

Ξ_κ

. We validate CG-MuTra on a Unitree G1 humanoid across grass, slopes (

10^\circ

--

15^\circ

), and gravel in both simulation and hardware. Experimental results demonstrate that CG-MuTra achieves smooth, highly robust fall recovery and locomotion transitions across multiple terrains while maintaining a single deployable policy.

Xiaoyu Xu, Zhiming Chen, Yuenan Zhao +2

School of Control Science and Engineering, Shandong University, Jinan, 250061, China · Key Laboratory of Machine Intelligence and System Control, Ministry of Education, China

Humanoid Robot Locomotion Robot Failure Recovery Terrain-Aware Robot Locomotion Robot Locomotion Robust RL Humanoid Robotics

Jun 7, 2026cs.RO

Real-IKEA: Physical Fidelity is the Prerequisite for Robust Manipulation

Robotic manipulation robustness often founders on the physics gap between simplified simulations and the resistance-laden real world. In this work, we emphasize that physical realism in articulated interaction is an important ingredient for robust policy learning. We present Real-IKEA, a dataset and simulation framework designed with physical accuracy as a first-class goal. Real-IKEA provides 1,079 articulated asset configurations, derived from 83 authentic IKEA handles and knobs processed through a meticulous six-step physical workflow. For contact-geometry accuracy, we introduce a bidirectional surface-deviation metric to quantify collision meshes. For dynamics realism, we establish resistance-calibrated configurations that vary damping and friction. Crucially, we demonstrate through a Reinforcement Learning (RL) policy that high-fidelity assets enable the discovery of robust "hooking" and "levering" strategies that prioritize mechanical advantage over fragile friction-pulling. Together, these results position Real-IKEA as a critical benchmark for developing manipulation policies capable of human-level robustness in articulated object tasks.

Kunqi Xu, Zhenhao Huang, Siyuan Luo +2

Human-centered Robotic Lab, National University of Singapore · School of EECS, Peking University

Contact-Rich Robotic Manipulation Robotics Simulation Robot Manipulation Benchmarks Articulated Object Manipulation Robust RL

Jun 7, 2026cs.RO

Towards End to End Motion Planning and Execution for Autonomous Underwater Vehicles Using Reinforcement Learning

Autonomous Underwater Vehicles (AUVs) traditionally rely on complex, heavily engineered pipelines for perception, path planning, and motion control. This paper explores the feasibility of an end-to-end Deep Reinforcement Learning (DRL) approach that maps raw sensor data directly to thruster commands, reducing manual engineering. We propose a hierarchical reinforcement learning (HRL) architecture splitting the problem into two Markov Decision Processes. A High-Level (HL) policy operating at 2Hz processes raw

84 \times 84

pixel monocular camera frames, stacked

100 \times 100

pixel forward-looking imaging sonar, and proprioceptive data to generate spatial subgoals. Simultaneously, a Low-Level (LL) policy operating at 10Hz converts these subgoals into thruster commands. The HL policy is trained using Reinforcement Learning from Prior Demonstrations (RLPD) within a modified Sample-Efficient Robotic Reinforcement Learning (SERL) framework, while the LL policy utilizes Soft Actor-Critic (SAC) combined with Hindsight Experience Replay (HER). Evaluated in the high-fidelity HoloOcean simulator, our method demonstrates successful obstacle avoidance, achieving trajectory lengths closely approximating (within 4% to 6% of) an

\text{RRT}^*

planning baseline. Furthermore, the learned policy exhibits strong robustness to simulated sensor noise and decreased visibility. While the system navigates familiar geometries effectively, experiments reveal generalization limitations when encountering unvisited areas with novel obstacle shapes. Ultimately, this work demonstrates the promise of sample-efficient, end-to-end DRL for underwater navigation using minimal computational hardware.

Elisei Shafer, Oren Gal

Department of Marine Technologies, University of Haifa, Israel

Hierarchical RL Visuomotor Policy Learning Underwater Robotics Autonomous Underwater Navigation Robust RL

Jun 7, 2026cs.LG

Adaptive Loss Balancing for Noise-Robust GRPO in Generative Recommendation

Reinforcement learning (RL) presents a promising avenue for enhancing generative recommendation beyond supervised imitation, leveraging reward signals to guide policy improvement. However, its efficacy is critically contingent on the trustworthiness of the reward model for the samples it evaluates. In practice, production rankers, the widely adopted reward models, are trained on exposure-biased logs, leading to sample-dependent inaccuracies that violate this assumption. Our stratified analysis uncovers a consistent pattern: reward guidance is most beneficial when the policy exhibits uncertainty and the ranker can effectively discriminate the ground-truth item from rollout negatives. On other samples, the reward signal is either negligible or detrimental, highlighting the risk of uniform RL application. To address such an issue, we introduce AdaGRPO, a novel framework that treats reward-guided optimization as selective admission rather than uniform pressure. Training is anchored in supervised negative log-likelihood, while the GRPO objective is gated by a binary, per-sample clip determined by two rollout diagnostics: policy-side difficulty and reward discriminability. Instances failing either diagnostic default to pure supervision, ensuring stability and mitigating the amplification of noisy gradients. We validate AdaGRPO on a large-scale e-commerce dataset. At the best intermediate checkpoint, it elevates HR@10 from 11.01% to 12.18% while constraining hallucination below 0.22%, and maintains robustness at the final checkpoint (HR@10 11.63%, hallucination 0.27%), outperforming fixed NLL--GRPO mixtures across the retrieval--validity frontier. In production A/B tests, AdaGRPO achieves statistically significant gains in click-through rate and dwell time, confirming its practical utility.

Kewei Xu, Junbo Qi, Yanyan Zou +3

Waseda University Tokyo, Japan · University of Electronic Science and Technology of China Chengdu, China

Group Relative Policy Optimization Recommender Systems Robust RL Generative Recommendation

Jun 5, 2026cs.RO

Predictive Style Matching: Natural and Robust Humanoid Locomotion

Reinforcement learning has become the prevailing approach to humanoid locomotion control: policies transfer reliably from simulation to hardware and recover gracefully from disturbances. Motion quality, however, still lags behind: task-only rewards often converge to stiff, asymmetric gaits, while motion imitation methods improve appearance but become more sensitive to external disturbances because reference signals can oppose the transient poses needed to regain balance. We propose Predictive Style Matching, in which an offline predictor maps the robot's lower-body state history and velocity commands to interpretable upper-body joint and gait targets that shape the rewards during training. Because the targets are state-conditioned rather than time-indexed and the predictor is used only at training time, the deployed controller inherits the proprioceptive interface and inference cost of a task-only RL baseline. On the Unitree G1, in both simulation and hardware, PSM reduces upper-body style error by roughly an order of magnitude over task-only RL while preserving its fall-recovery rate, whereas the motion-imitation baseline attains the lowest style error but fails to recover from disturbances about five times as often.

Simeon Nedelchev, Ekaterina Chaikovskaia, Egor Davydenko +2

Moscow Institute of Physics and Technology (MIPT), Dolgoprudny, Moscow Region, Russia · Innopolis University, Innopolis, Russia · Sber Robotics Center, Moscow, Russia

Humanoid Robot Locomotion Reward Shaping Robot Locomotion RL for Legged Locomotion Robust RL

Jun 4, 2026cs.MA

Learning to Contest: Decentralized Robust Fairness in Cooperative MARL via Cross-Attention

Fair cooperative multi-agent reinforcement learning (MARL) teams that maximize an egalitarian welfare are exploitable: a single self-interested agent free-rides on the surplus that fair agents forgo to raise the worst-off, and the known remedy is a centralized need-based allocator. We show that a decentralized defense becomes possible once contention is graded: when a contested resource still delivers a fraction

1-c

, a worst-off cooperator that contests a free-rider strictly improves on yielding, so leverage exists for every

c < 1

. We introduce CAN, a permutation-equivariant cross-attention policy over agents' observed behaviour that infers how many free-riders are present and responds proportionally -- turn-taking when none, contesting just enough when some. Trained against an adversarial league, CAN keeps best-response exploitability near the centralized oracle (

ρ\approx 1.2\text{--}1.5

vs.

ρ= N

unprotected) at essentially no efficiency cost, whereas the fair-MARL learners (GGF, FEN, SOTO) each collapse to an exploitable or wasteful extreme. Giving those objectives CAN's identical adversarial training does not rescue them, so the objective -- not adversarial training alone -- is what makes hardening possible. Against a committed (non-adaptive) defector, every learned defense including ours provides deterrence rather than immunity, weakening as the leverage

(1-c)/2

vanishes. Across further environments and team sizes the same principle sets the scope: robustness holds exactly as far as the game's contest leverage reaches, and we map that boundary rather than claim to remove it.

Can Savcı

Independent Researcher Izmir, Turkey

Robust RL Cooperative MARL Multi-Agent Reinforcement Learning

Jun 3, 2026cs.RO

HORIZON: Recoverability-Governed Curriculum for Physical-Domain Scaling

Scaling robust robot policies requires more than broader randomization, because physical-domain experience must remain organized and learnable throughout training. We study when a policy can benefit from harder physics and identify recoverability as a central constraint in on-policy physical-domain scaling. In on-policy training, new dynamics are useful only insofar as they remain close enough to the current policy to generate corrective on-policy data, rather than collapsing rollouts into unrecoverable failures. Using quadruped locomotion as a physically demanding benchmark for embodied generalization, we introduce HORIZON, a checkpointed frontier curriculum that expands physical domains only within the current policy's recoverable boundary. HORIZON uses rollback and boundary refinement to govern each expansion step, turning fixed randomization into a continual process of physical-domain growth. Experiments reveal three regularities of physical-domain expansion. First, direct domain widening is uneven across physical axes and often unlearnable without staged ordering. Second, domain composition is non-monotonic, and adding more domains beyond a compact core can dilute recoverable joint samples and reduce overall robustness. Third, offline distillation of isolated experts cannot substitute for the joint interaction generated by on-policy curriculum. Together, these results frame physical-domain generalization as a continual growth problem for embodied control, with recoverability as the organizing principle for on-policy expansion.

Chenhao Bai, Liqin Lu, Kaijun Wang +5

1Zhejiang University, State Key Lab of CAD & CG · 2Zhejiang University of Technology

Domain Randomization Curriculum RL RL for Legged Locomotion Robot Policy Generalization Robust RL

Jun 3, 2026cs.LG

Scenario Generation for Risk-Aware Reinforcement Learning with Probably Approximately Safe Guarantees

Guaranteeing safety is critical to the deployment of reinforcement learning (RL) agents in the real-world, especially as policies learned using deep RL may demonstrate susceptibility to transition perturbations that result in unknown or unsafe behaviour. A method of policy verification is to construct probabilistic barrier-certificates by sampling policy trajectories with respect to safety constraints, thereby demarcating known safe behaviour from unknown behaviour. Obtaining tight upper and lower bounds on the probability of violation of these constraints may be difficult if the policy is susceptible to transition uncertainty or perturbation that places the agent in insufficiently explored states. To address this, we approximate the distribution of the encountered state-space using a variational autoencoder (VAE) and construct upper and lower-bound barrier-certificates using latent characteristics of states to optimize for regions of known, safe behaviour with high confidence. We frame this in our work as a dual optimization problem where the lower-bound barrier-certificate presents a more conservative estimate of the safe region than the upper-bound barrier-certificate. Sampling states that lie within the set difference of the two during training, i.e. the non-robust region, allows us to tighten the upper and lower bounds to provide sharper probabilistic guarantees on safety. Within our study, we describe the guarantees placed and demonstrate the tightness of our bounds experimentally.

Mohit Prashant, Arvind Easwaran

Nanyang Technological University

Control Barrier Functions Risk-Sensitive RL Safe RL Robust RL

Jun 3, 2026cs.LG

Policy Gradient for Continuous-Time Robust Markov Decision Processes

The framework of robust Markov decision processes (RMDPs) allows the design of reinforcement learning agents that satisfy performance guarantees under worst-case transition dynamics. Traditional RMDPs consider discrete-time dynamics and recently, sample-efficient policy gradient algorithms have been considered in this context. This paper investigates policy gradient algorithms within a continuous-time RMDP framework. Policy gradients and adversarial gradients are derived using pathwise and adjoint-based formulas for stochastic and ordinary differential equations. We propose double-loop optimisers to obtain linear convergence in the oracle-based setting and an

\tilde{\mathcal{O}}(\frac{1}{ε^2})

sample complexity in the sample-based setting in an analysis which also derives novel tools for the framework of undiscounted total cost MDPs. Additionally, we propose mean-field optimisers as distributional optimisers with an

\tilde{\mathcal{O}}(\frac{1}{K})

oracle-based convergence rate and an

\tilde{\mathcal{O}}(\frac{N^2}ε)

sample complexity under

N

-particle approximation. The effectiveness of continuous-time policy gradient algorithms is confirmed for both optimisers on continuous-time RMDPs with neural ordinary differential equation dynamics.

Tanya Veeravalli, David M. Bossens, Atsushi Nitanda

Centre for Frontier AI Research, Agency for Science, Technology and Research (A*STAR) · Institute of High Performance Computing, Agency for Science, Technology and Research (A*STAR) · College of Computing and Data Science, Nanyang Technological University

Robust Markov Decision Processes Markov Decision Processes Continuous-Time RL Policy Gradient Methods Robust RL Policy Learning

Jun 2, 2026cs.LG

Post-Hoc Robustness for Model-Based Reinforcement Learning

To improve the real-world applicability of reinforcement learning (RL), the field of adversarially robust RL studies how to train agents under adversarial environment perturbations. In this setting, a protagonist agent optimizes a policy under environmental perturbations from an adversary, resulting in a zero-sum Markov game. When adversarially robust RL is combined with model-based RL, the adversary can target a learned transition model instead of the training environment. Extending this idea, this work introduces post-hoc robustification of deep RL agents at inference time. By using the learned model in combination with a trained nominal policy, our approach performs a robust policy improvement step. The goal is to improve robustness without any additional training of neural networks. Specifically, we utilize model-predictive control under adversarial rollouts, which are approximated via projected gradient descent within a bounded uncertainty set. Furthermore, these offline rollouts are performed while considering and mitigating out-of-distribution issues. The proposed methodology is validated by demonstrating significant improvements in robustness when the algorithm is evaluated in perturbed Gymnasium MuJoCo environments, while considering the computational limitations of the post-hoc inference setting.

Siemen Herremans, Ali Anwar, Siegfried Mercelis

1IDLab - University of Antwerp, imec

Adversarial Robustness Robust RL Model-Based RL

Jun 2, 2026cs.RO

PerchRL: Vision-Based Agile Perching on Inclined Platforms under Rapid and Irregular Motion

Autonomous vision-based perching of quadrotors on moving inclined platforms is critical for air-ground collaboration but remains challenging due to the limited field of view (FOV). In this paper, we propose PerchRL, a reinforcement learning (RL) framework for vision-based agile perching on inclined platforms under rapid and irregular motion. Specifically, we employ a two-stage learning strategy consisting of state-based pre-training followed by vision-based fine-tuning. To improve generalization across diverse platform motions, we employ randomized platform trajectories to prevent overfitting and temporal augmentation methods to capture latent motion patterns from historical observations. During vision-based fine-tuning, a hybrid learning framework consisting of visibility-aware state augmentation and active perception rewards is presented to improve robustness under intermittent visual loss. Extensive simulation and real-world experiments demonstrate the feasibility, stability, and real-time performance of PerchRL, while successful deployment across distinct quadrotor platforms further validates its adaptability. The source code will be released to benefit the community.

Zihong Lu, Zongzhuo Liu, Huaxu Li +5

1SUSTech · 2HITSZ · 3PCL +1

RL for Robotics Aerial Robotics Quadrotor Control Vision-Based Robot Control Robust RL

Jun 2, 2026cs.LG

Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions

While Proximal Policy Optimization (PPO) demonstrates strong performance in stationary settings, we show that its standard optimization paradigm struggles in continual and non-stationary environments. The failure does not stem from insufficient model capacity or overly restrictive clipping. Instead, PPO performs persistent, directionally inefficient local updates, which indicates a lack of geometry-aware guidance for accumulating meaningful behavioral change and ultimately hindering transitions toward new behavior patterns. Although divergence-based regularization introduces partial geometric awareness, its monotonically increasing penalties implicitly discourage large policy deviations, even when such shifts are necessary for effective adaptation. To address this limitation, we propose Gaussian Trust Region Policy Optimization (GTR), which reshapes the trust region using a Gaussian kernel. The resulting constraint is bounded and non-monotonic, providing strong local stability while progressively relaxing under sustained high-advantage updates. To further improve robustness, we introduce a Mixture Gaussian Anchor that adapts to recent policy trajectories, reducing variance induced by stale references. GTR is architecture-agnostic and achieves strong performance across games, simulated robotic control, open-world exploration, and language model post-training. These results demonstrate that geometry-aware trust-region design can be a promising direction for robust reinforcement learning in complex non-stationary environments. Our code is available at https://anonymous.4open.science/r/GTR_demo/README.md.

Bingxu Liu, Jiashun Liu, Johan Obando-Ceron +5

Hong Kong University of Science and Technology · Fudan University · Mila - Québec AI Institute +2

Non-Stationary RL Reinforcement Learning Policy Gradient Methods Proximal Policy Optimization Trust Region Policy Optimization Robust RL

Jun 1, 2026cs.RO

Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy Adaptation

Real-world dynamics shifts pose a critical challenge for reinforcement learning in robotics, as policies tightly coupled to nominal environments often fail catastrophically when physical conditions change. Most existing methods rely on encoding explicitly identified physical parameters into a latent context, a parameter-centric paradigm that depends on pre-specified axes of variation and becomes brittle under unmodeled or compound dynamics changes. We revisit dynamics adaptation from an outcome-centric perspective: rather than telling policies what the dynamics are, we enable them to learn how dynamics affect interaction outcomes. Theoretically, this is grounded in a monotonic relationship between target-domain regret and the Lipschitz constant of a trajectory dynamics encoder. Practically, this constant can be upper-bounded through contrastive learning, yielding a smooth, task-relevant latent topology without privileged dynamics information. On MuJoCo benchmarks, our method consistently outperforms parameter-centric baselines under severe dynamics shifts, including unmodeled and time-varying parameters, while also improving in-distribution stability and latent interpretability. Overall, these results validate that controlling latent geometry is a principled mechanism for robust adaptation.

Zhiming Xu, Weitao Zhou, Xianghui Pan +4

School of Computer Science and Engineering, Tongji University, Shanghai, China · School of Vehicle and Mobility, Tsinghua University, Beijing, China · Simple AI, Beijing, China +1

Robot Policy Adaptation Latent Dynamics Modeling Robot Dynamics Learning Robotic RL Robust RL

May 29, 2026cs.RO

DRL-Based Pose Control for Double-Ackermann Robots Under Actuation Uncertainties

Robust deployment of deep reinforcement learning (DRL) policies on real robots remains challenging due to discrepancies between simulation and real-world dynamics. We address this issue in the context of maneuvering with double-Ackermann-steering mobile robots, which introduce additional constraints due to their non-holonomic nature. Building upon the DRL framework ManeuverNet, we extend its objective from position control to full pose control, resulting in a more challenging task. We further investigate the impact of actuation-related uncertainties on policy transfer. The use of simplified actuation models during training of the extended policy can lead to poor generalization, shown by a success rate drop from 100% in PyBullet to 25% in Gazebo under stricter evaluation conditions. To address this limitation, we adopt a sim-to-sim-to-real approach, where actuation effects observed in Gazebo are incorporated into the PyBullet training environment. Using multi-environment DRL with SAC and CrossQ, we learn policies that remain robust despite modeling inaccuracies. This approach can significantly reduce the performance gap across simulators, achieving up to 92% success rate in Gazebo and maintaining 69% under stricter thresholds, with successful transfer to a real robot without additional tuning.

Oussama Zaim, Mélodie Daniel, Aly Magassouba +2

Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, F-33400 Talence, France. · School of Computer Science, University of Nottingham, UK. · Instituto de Investigación en Ingeniería de Aragón (I3A), Universidad de Zaragoza, 50018 Zaragoza, Spain.

Robotic Control Robotics Simulation Sim-to-Real Transfer Robust RL

May 29, 2026cs.RO

Physical Atari: A Robust and Accessible Platform for Real-time Reinforcement Learning on Robots

We built a robot called the Robotroller that actuates an Atari CX40+ controller and a device called the Atari Devbox that renders the game frame and the reward signal from the Arcade Learning Environment on a screen. The Robotroller and the Atari Devbox, together with an off-the-shelf camera and a desktop computer, constitute a system that can be used to study reinforcement learning algorithms in the physical world. We call the full system Physical Atari. In this paper, we detail the key decisions that make Physical Atari a robust and accessible platform. To make the system robust, we designed the Robotroller so that all movement is done through bearings, which reduces wear. Additionally, we wrote software that monitors the state of the servos at a high frequency and intervenes to limit stress. To make the system accessible, we used affordable off-the-shelf components and parts that can be manufactured using consumer 3D printers. Physical Atari can be built for under $1,000 and has been used for weeks of non-stop reinforcement learning experiments without any mechanical failures. We used it to validate that reinforcement learning algorithms can learn directly on robots and show that even small distribution shifts between learning and deployment can significantly degrade the performance of policies. Our results underscore the importance of on-device adaptation for strong performance on robots.

Khurram Javed, Joseph Modayil, Gloria Kennickell +2

Keen Technologies · Openmind Research Institute · University of Alberta, Canada

RL Benchmarks Reinforcement Learning Robotic RL Robust RL

May 29, 2026cs.AI

Robust Shielding for Safe Reinforcement Learning

Shielding is an effective approach to formally guarantee the safety of reinforcement learning agents in Markov decision processes (MDPs). However, existing shielding techniques typically assume knowledge of the safety-relevant transition dynamics - a requirement that is seldom met in practice. To address this limitation, we introduce a novel shielding framework for robust MDPs (RMDPs), i.e., MDPs with sets of transition probabilities. We define safety as the satisfaction of a linear temporal logic (LTL) formula with a certain threshold probability under the worst-case transition probabilities of the RMDP. We prove that our shielding framework is both sound and optimal for the RMDP: every policy admissible by the shield is safe, and conversely, every safe RMDP policy is admissible by the shield. We combine our approach with existing sampling methods for learning transition probabilities of MDPs with probably approximately correct (PAC) guarantees. This combination enables the construction of shields for MDPs that, with high confidence, guarantee safety while remaining minimally restrictive. Our experiments show that our shields for learned RMDPs guarantee safety in unknown MDPs while recovering strong expected return as the number of samples increases.

Edwin Hamel-De le Court, Thom Badings, Alessandro Abate +2

Department of Computer Science, University of Manchester, United Kingdom · Faculty of Computer Science & DSME, RWTH Aachen University, Germany · Department of Computer Science, University of Oxford, United Kingdom +1

Robust Markov Decision Processes Formal Verification Safe RL Robust RL

May 29, 2026cs.CV

StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement

Video world models (WMs) have shown promise for policy evaluation and improvement by imagining realistic future observations conditioned on ego-robot actions. While WMs can model distributions over futures, policy evaluation and improvement typically rely on nominal imaginations, which can miss high-impact outcomes of robot actions unless prohibitively many samples are drawn. To enable robust policy evaluation and improvement over WM imaginations, we propose StressDream, which steers imaginations toward high-impact yet plausible outcomes specified at inference time by optimizing the initial noise of diffusion-based WMs. However, optimizing high-dimensional noise is challenging: the optimization must reason about nuanced, scene-dependent target events in generated videos while avoiding out-of-distribution (OOD) noise that yields implausible imaginations. We address this with two complementary objectives: a semantic objective with a Vision-Language Model that provides informative gradients by reasoning about the generated video, and a plausibility objective that prevents the optimized noise from drifting OOD. With state-of-the-art video world models for autonomous driving and robotic manipulation, we show that StressDream effectively steers imaginations toward high-impact yet plausible outcomes specified by text at inference time, such as task failures, enabling robust policy evaluation and improvement by identifying actions whose plausible futures include undesirable outcomes. Video results are available at https://stressdream.github.io/.

Junwon Seo, Sushant Veer, Ran Tian +6

Carnegie Mellon University · NVIDIA Research · University of Washington +1

Video Diffusion Models Action-Conditioned World Models Robotic Policy Evaluation Robust RL Model-Based RL Video World Models

May 28, 2026cs.RO

VE2VF: Vision-Enabled to Vision-Free Distillation via Real-world Reinforcement Learning for Robust Contact-Rich Manipulation

When using reinforcement learning (RL) for contact-rich robotic manipulation, vision can provide task-relevant information that complements robot proprioception. However, vision-enabled policies tend to overfit to the visual conditions seen during training, limiting their robustness and transferability. We present a human-in-the-loop RL framework that employs teacher-student distillation to achieve robust performance across multiple task variants, trained entirely in the real world without requiring domain randomization or data augmentation. A vision-enabled teacher distills its knowledge into a vision-free student that relies solely on pose, twist, and wrench sensing, combining fast training with strong task generalization. On the real-world NIST assembly benchmark board, our approach achieves 95% overall success after approximately 50 minutes of training on 3 representative tasks, including robust generalization to 8 unseen task variants. Fine-tuning with distillation achieves full success on the most challenging task. We demonstrate that the resulting policies outperform baselines in both robustness and adaptability. Page: https://tuwien-asl.github.io/VE2VF/.

Victor Kowalski, Chengxi Li, Dongheui Lee

Autonomous Systems, Technische Universitaet Wien (TU Wien), Vienna, Austria · Institute of Robotics and Mechatronics (DLR), German Aerospace Center, Wessling, Germany

Cross-Modal Knowledge Distillation Robot Skill Learning Contact-Rich Robotic Manipulation Generalization in Robotic Manipulation Robotic RL Robot Policy Generalization+2

May 27, 2026cs.LG

Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning

Model-based reinforcement learning (MBRL) agents typically learn world models by minimizing predictive loss. However, powerful RL optimizers inevitably exploit minor model inaccuracies, leading to simulator exploitation and a reality gap where policies succeed in simulation but fail in the real world. We propose that the objective for learning simulators should be strategic robustness rather than predictive accuracy, and formulate this as a zero-sum minimax game between a model player and an adversarial policy player. We provide a comprehensive theoretical analysis: (1) an online learning guarantee showing the game is learnable with sublinear regret bounds; (2) a tractable critic-based simplification bounding the global policy-value gap by the local critic's loss; and (3) an Error-MDP duality, proving that finding the worst-case policy is formally dual to a standard RL problem where the reward is the one-step critic error. This duality yields a provably convergent active data selection algorithm. Experiments on continuous control tasks demonstrate that our approach reduces prediction error in strategically important regions by

1.5

-

2.2\times

and enables policies trained purely in simulation to match near-optimal real-world performance.

Christoph Dann, Yishay Mansour, Mehryar Mohri

Google Research · Tel Aviv University and Google Research · Google Research and Courant Institute of Mathematical Sciences

Sim-to-Real Transfer Active Learning Robust RL Model-Based RL

May 26, 2026cs.AI

Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments

Recent advances in large language models (LLMs) have facilitated the widespread deployment of LLMs as interactive agents capable of reasoning, planning, and tool use. Despite strong performance on existing benchmarks, such agents often exhibit notable degradation when deployed in real-world settings, where environments are inherently stochastic and imperfect. We argue that this discrepancy arises from a fundamental mismatch between idealized training settings and real-world interaction dynamics, where current paradigms rely on carefully curated task instructions and stable, well-controlled environments. To address this gap, we propose NoisyAgent, an agentic training framework that explicitly incorporates environmental imperfections into the agent learning process. We identify two major sources of interaction noise in real-world scenarios: user noise, which captures ambiguity and variability in user interaction, and tool noise, which reflects failures and anomalies in tool execution. We introduce such perturbations into the training pipeline by modifying user interaction patterns and simulating tool execution results within the training environment. To stabilize training while encouraging agents to handle increasingly challenging imperfections, noise is applied to only a subset of rollouts and progressively increased in difficulty as the model adapts to the current noise level. Extensive experiments demonstrate that our approach consistently improves agent robustness under noisy and dynamic environments. Our analysis reveals that training under noise conditions also yields performance gains on idealized benchmarks, suggesting that controlled exposure to environmental noise promotes more generalizable reasoning and decision-making behaviors. Our findings highlight the importance of modeling interaction imperfections for bridging the gap between agent training and real-world deployment.

Yuxin Chen, Xiaodong Cai, Junfeng Fang +9

National University of Singapore · Meituan · Tsinghua University +2

LLM Agents LLM Agent Training Robust RL LLM Agent Reliability

May 26, 2026cs.RO

Credibility-Aware Learning and Control for Safe USV Navigation under Perception Uncertainty

Safe navigation for Unmanned Surface Vehicles (USVs) under the International Regulations for Preventing Collisions at Sea (COLREGs) remains challenging in dynamic maritime environments, especially when perception uncertainty is miscalibrated. Errors in state estimation can produce unreliable belief states that mislead value learning, while logic based on discrete traffic rules can cause abrupt action corrections. To address these challenges, we integrate Credibility-Weighted Value Learning (CWVL) with Covariance- and Recovery-Aware Control Barrier Function Quadratic Programming (CoReCBF-QP). CWVL derives a dynamic trust factor from the discrepancy between the covariance estimated by the filter and empirical error statistics. This factor modulates the critic's heteroscedastic loss and limits overfitting to miscalibrated observations. CoReCBF expands the collision geometry according to uncertainty and incorporates terms for braking and turning recovery. The resulting hyperbolic safety boundary preserves feasible avoidance velocities and supplies the QP safety constraint. A continuous COLREGs-aware reference in the objective promotes starboard maneuvers in Rule 14 head-on and Rule 15 give-way crossing encounters. Simulations show improved robustness in collision avoidance and COLREGs event compliance, achieving an 82.0% success rate with ten target ships beyond the training range.

Yuhang Zhang, Shuqi Chai, Yukang Zhang +5

School of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China · Shenzhen Research Institute of Big Data, Shenzhen 518172, China · Chinese University of Hong Kong, Shenzhen, Shenzhen 518172, China +5

Collision Avoidance Robot Navigation Control Barrier Functions Safe RL Robust RL Robot Collision Avoidance

May 26, 2026quant-ph

Adaptive Reinforcement Learning for Robust Open Quantum System Control: A Multi-Task Framework with Temporal Optimization

We present a Multi-task Soft Actor-Critic (SAC) Reinforcement Learning framework designed for open-system quantum control across diverse Hamiltonians, which learns optimal pulse sequences while simultaneously discovering problem-specific evolution time T and number of control pulse segments N. Experimental results across 51 Hamiltonian variations demonstrate that the multi-task SAC model is able to generate control pulses that can drive a system, under environment noise, from its initial state to its target state with high fidelities, establishing essential foundations for universal quantum control applicable to realistic noisy quantum devices. Through progressive expansion of the training Hamiltonian set, we investigate if a single multi-task model trained using a given number of sample Hamiltonians can successfully accomplish state-transfer tasks for Hamiltonians drawn from the same Hamiltonian space but not encountered during training. In addition, our Robustness Infidelity Measure (RIM) analysis reveals that SAC trained policies exhibit superior robustness to pulse amplitude perturbations and decoherence rate variations compared to GRAPE-optimized controls.

Haftu W. Fentaw, Steve Campbell, Simon Caton

School of Computer Science, University College Dublin, Belfield, Dublin 4, Dublin, Ireland. · Centre for Quantum Engineering, Science, and Technology, University College Dublin, Belfield, Dublin 4, Dublin, Ireland. · School of Physics, University College Dublin, Belfield, Dublin 4, Dublin, Ireland.

RL Control Multi-Task RL Soft Actor-Critic Quantum RL Robust RL Optimal Control

May 26, 2026cs.RO

Robust Koopman Control Barrier Filters for Safe Actor-Critic Reinforcement Learning

Safe reinforcement learning (RL) for robotic systems requires policies that improve task performance while satisfying state and input constraints during both training and deployment. Control barrier functions (CBFs) provide a principled mechanism for enforcing forward invariance through minimally invasive safety filters, but their use in model-free RL is limited by the need for accurate dynamics and hand-designed barrier certificates. We propose Robust Koopman-CBF SAC, a safety-filtered actor--critic framework that learns a finite-dimensional Koopman predictor from data, constructs affine CBF constraints in the lifted space, and enforces them through a quadratic-program safety layer. To account for finite-dimensional Koopman approximation error, the CBF condition is tightened using a projected residual margin estimated from held-out rollout data. The critic is trained on the executed safe action, while the actor is regularized toward the Koopman-CBF feasible set, reducing dependence on the filter over training. Across safe-control benchmarks, the method achieves zero constraint violations on CartPole stabilization and tracking while matching or exceeding unconstrained SAC returns. On high-dimensional Safety Gymnasium locomotion tasks, the method reduces violations in some settings but also exposes important limitations of first-order velocity barriers and linear EDMD models, motivating high-order and multi-step Koopman-CBF extensions. These results suggest that robust Koopman-CBF filters are a promising bridge between model-free RL and certifiable safety, while clarifying the structural conditions under which such filters remain effective.

Dhruv S. Kushwaha, Zoleikha A. Biron

Koopman Operator Learning Control Barrier Functions Safety Filtering Safe RL Robust RL

May 25, 2026cs.MA

Decoupled Delay Compensation: Enhancing Pre-trained MARL Policies via Learned Dynamics Filtering

Real-world multi-agent reinforcement learning (MARL) systems must often operate under stale observations, stochastic communication delays, and intermittent packet loss. Policies trained under idealized synchronous conditions frequently exhibit significant performance degradation in these regimes because they act on outdated feedback. We propose a modular execution-stage state-estimation layer that replaces delayed communicated observations with current belief-state estimates. The framework integrates a learned Gated transition model with a recursive Kalman filtering layer to estimate instantaneous states from asynchronous measurements. A primary advantage of this approach is its modularity, The estimator serves as a plug-in for pre-trained policies, requiring no modifications to the original MARL training algorithm, architecture, or reward structure. Evaluation across diverse multi-agent and continuous-control benchmarks demonstrates that the proposed layer consistently enhances robustness to communication latency and message loss. The most significant performance gains are observed in coordination-intensive and dynamically unstable tasks where temporal consistency is critical for control.

Maxim Mednikov, Oren Gal

University of Haifa, Israel

Robust RL Multi-Agent Reinforcement Learning

May 23, 2026cs.RO

Vision-Guided Outdoor Flight and Obstacle Evasion via Reinforcement Learning

Although quadcopters boast impressive traversal capabilities enabled by their omnidirectional maneuverability, the need for continuous pilot control in complex environments impedes their application in GNSS and telemetry-denied scenarios. To this end, we propose a novel sensorimotor policy that uses stereo-vision depth and visual-inertial odometry (VIO) to autonomously navigate through obstacles in an unknown environment to reach a goal point. The policy is comprised of a pre-trained autoencoder as the perception head followed by a planning and control LSTM network which outputs velocity commands that can be followed by an off-the-shelf commercial drone. We leverage reinforcement and privileged learning paradigms to train the policy in simulation through a two-stage process: 1) initial training with optimal trajectories generated by a global motion planner acting as a supervisory backbone, 2) further fine-tuning in a curriculum environment. To bridge the sim-to-real gap, we employ domain randomization and reward shaping to create a policy that is both robust to noise and domain shift. In outdoor experiments, our approach achieves successful zero-shot transfer to both obstacle environments and a drone platform that were never encountered during training.

Shiladitya Dutta, Aayush Gupta, Varun Saran +1

College of Engineering, Department of Electrical Engineering and Computer Science, University of California Berkeley

RL for Robotics UAV Navigation Visuomotor Policy Learning Dynamic Obstacle Avoidance Robust RL

May 23, 2026cs.LG

Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPs

In online reinforcement learning, data scarcity creates epistemic uncertainty that makes robustness important early in learning, whereas sufficient exploration is needed to learn the true-environment optimal policy. We study this time-varying robustness--exploration trade-off through a quantile Bayesian risk-aware Markov decision process (BR-MDP), in which the quantile level controls how posterior uncertainty enters the Bellman backup. We characterize this control through an asymptotic normality result for the difference between the quantile BR-MDP value and the value in the true environment. The result implies that upper/lower-tail quantiles induce optimism/pessimism towards epistemic uncertainty, and the magnitude of the optimism/pessimism decreases as data accumulate. Building on this characterization, we propose an online Bayesian risk-aware algorithm with an adaptive quantile schedule that emphasizes robustness early and gradually encourages exploration of less-visited state--action pairs. We establish sublinear Bayesian regret bounds with respect to both the true optimal value and the optimal BR-MDP robust value. Numerical experiments demonstrate strong performance in both exploration-demanding and exploration-costly environments.

Meichen Song, Yuhao Wang, Enlu Zhou

School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta, GA 30332, USA

Reinforcement Learning Bayesian RL Risk-Sensitive RL RL Exploration Robust RL

May 22, 2026cs.LG

Infra-Bayesian Reinforcement Learning Agents Outperform Classical RL For Worst-Case Robustness

Classical reinforcement learning assumes the agent interacts with a fixed environment whose behavior does not depend on the agent's policy. This assumption breaks down in non-realizable settings where other actors might anticipate the agent's behavior, including environments crucial to AI safety, where the agent interacts with predictors, humans, other AI agents, and institutions. In such settings, the agent's model class fails to capture the world in which it operates. Under such misspecification, classical Bayesian methods can produce confidently wrong posteriors, unreliable decisions, and unbounded regret, as realizability fails to obtain. Infra-Bayesianism is a decision-theoretic framework that addresses these failures by distinguishing ordinary probabilistic uncertainty, where priors can be reasonably chosen, from Knightian uncertainty, where no grounds exist for the construction of such a prior. It does so by evaluating actions on their worst-case outcomes, rather than from posterior expectations or weighted averaging. We present the first proof-of-concept implementation of an infra-Bayesian reinforcement learning architecture for finite-outcome stateless decision problems. Our agent maintains a set of imprecise hypotheses, updates them using infra-Bayesian conditioning, and selects actions by maximizing worst-case expected value. We apply this implementation of the infra-Bayesian maximin decision process to an environment with Knightian uncertainty, and demonstrate a lower worst-case regret as compared to classical reinforcement learning agents. We also investigate Newcomb's problem and show that the infra-Bayesian agent picks the optimal strategy, outperforming classical decision theory agents. Our results provide a step towards reinforcement learning agents that remain robust under model misspecification and policy-dependent uncertainty.

Manish Aryal, Faiyaz Azam, Agnivo Banerjee +11

Purdue University · Carnegie Mellon University · WorldQuant University +11

Reinforcement Learning Model Misspecification Robust RL Decision-Making under Uncertainty

May 20, 2026cs.MA

Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints

Communication enables coordination in multi-agent reinforcement learning (MARL), but many real-world applications, e.g., search-and-rescue with drone swarms, operate under severe bandwidth constraints. Many communication architectures still expose a coupled bottleneck in which a shared latent representation is used for both policy execution and inter-agent communication. Consequently, reducing message size directly limits the policy's latent space, often leading to significant performance degradation. We address this with two contributions. First, we introduce

β

, a normalised per-agent bandwidth budget that unifies sparsity, rounds, and message dimension into a single comparable constraint. Second, we provide SLIM, a minimal architecture that decouples the communication pathway from the policy's latent representation, allowing us to isolate the effect of bandwidth from the effect of policy capacity while benefiting from in-step communication. We evaluate our method on several partially-observable MARL benchmarks, where communication is essential. Our approach achieves state-of-the-art performance and exhibits scalability and robustness under limited communication, with only marginal degradation as bandwidth is reduced.

Alexi Canesse, Benoît Goupil, Jesse Read +1

École polytechnique (LIX), CNRS, Institut Polytechnique de Paris, Palaiseau, France

Decentralized MARL Multi-Agent Communication Robust RL Multi-Agent Reinforcement Learning

May 19, 2026cs.LG

When Critics Disagree: Adaptive Reward Poisoning Attacks in RIS-Aided Wireless Control System

Reward-poisoning attacks present a significant risk to learning-based wireless control systems. Given this, we propose a Disagreement-Guided Reward Poisoning (DGRP) adaptive attack on a Soft Actor-Critic (SAC) agent. In a Cognitive Radio Network (CRN) environment assisted by Reconfigurable Intelligent Surfaces (RIS), the SAC agent is tasked with maximizing the long-term secondary users' (SUs) rate by simultaneously optimizing the transmission power of the SU transmitter and the RIS phase shifts. DGRP corrupts rewards, particularly when the SAC dual critics exhibit substantial disagreement-especially in high-leverage, high-uncertainty states-resulting in distorted value estimations and guiding the policy towards suboptimal actions. Our findings demonstrate that DGRP substantially diminishes the performance improvements typically provided by RIS and degrades transmission quality. We further investigate key attack parameters and determine their impact on learning. In comparison to periodic-timing and exploration-triggered baselines, DGRP consistently causes greater damage, highlighting the necessity of considering disagreement-aware threats when evaluating the robustness of Deep Reinforcement Learning (DRL) in RIS-assisted networks.

Deemah H. Tashman, Soumaya Cherkaoui

Department of Computer and Software Engineering, Polytechnique Montreal, Montreal, Canada

Wireless Communications Robust RL

May 19, 2026cs.RO

RoHIL: Robust Human-in-the-Loop Robotic Reinforcement Learning Against Illumination Variations

Human-in-the-loop reinforcement learning systems achieve near-perfect success on the workstation where they are trained, but collapse when the same robot is moved to a workstation a few meters away due to shifts in the visual input distribution caused by new lamp positions and window light. Re-collecting demonstrations and re-running HIL on every workstation is incompatible with deployment, and naively fine-tuning on shifted-light data triggers catastrophic forgetting of the source workstation. To close this cross-domain gap, we present RoHIL, an offline fine-tuning framework that uses no extra real-robot interaction. RoHIL combines (i) a world-model-based image relighter that re-synthesises the visual stream of source-workstation trajectories under multiple virtual HDRI environments, leaving actions and rewards real; (ii) Illumination-Retention Replay (IRR), a data-level anti-forgetting mechanism that interleaves relit adaptation transitions with original-light retention transitions to preserve source-workstation Bellman coverage; and (iii) an anchored Bellman-actor regulariser that constrains representation and policy drift from the original source-workstation policy. Across four real-robot manipulation tasks under significant cross-workstation illumination variations, RoHIL substantially improves shifted-light performance where standard HIL-RL collapses, while preserving source-workstation performance, eliminating the need to re-collect data and retrain for every new workstation and environment. Project page: https://anonymous4365.github.io/RoHIL/

Shuoqin Zhang, Yixin Xiong, Xiru Gao +4

Chongqing University · Chengdu Anu Intelligence

Distribution Shift Robustness Robot Skill Learning Robotic RL Human-in-the-Loop AI Image Relighting Robust RL