Generalization in RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

The field asks whether an agent can act effectively when goals, layouts, visual inputs, dynamics, or collaborators differ from training, a requirement for reliable deployment. Common approaches include domain randomization and exploration for broader state coverage, invariant or task-conditioned representations, meta-learning, curricula, reusable skills, and Bayesian or model-based transfer. Researchers evaluate these methods in settings such as Procgen, MuJoCo, MetaWorld, DeepMind Control, robotics, and language-based agents, using held-out tasks, environments, and visual or dynamics shifts. A central tension is that diversity and regularization can improve transfer but hinder learning or retention, while benchmark design and metrics can make apparent generalization gains hard to interpret.

Latest papers

89 papers16 papers in the last four weeks, up 60% on the four weeks before. 0.1% of all new papers.

Mar 28, 2026

Factorization Regret mediates compositional generalization in latent space

Are there still barriers to generalization once all relevant variables are known? We consider the challenge of generalizing to a novel combination of task-relevant latent variables in the Cognitive Gridworld, a stationary Partially Observable Markov Decision Process where observations are generated by latent variables with parametric interactions. We establish Factorization Regret as an information-theoretic quantity measuring the contribution of latent variable interactions to task performance. Using this metric, we explain the sub-optimality of Echo State Networks and uncover a failure mode whereby confidence becomes decoupled from accuracy. This suggests that utilizing interactions between relevant variables is a non-trivial capability. We next introduce Representation Classification Chains to show that latent variable interactions and how to infer the variables' values can be learned together through Reinforcement Learning. Solving this variational inference problem enables generalization to novel combinations of relevant variables. Lastly, we demonstrate that once interactions are learned, imagined experience is sufficient for zero-shot control. In summary, we develop and motivate a minimal, theoretically grounded setting for research into generalization from experience.

John Schwarcz

Edmond & Lily Safra Center for Brain Sciences (ELSC), The Hebrew University of Jerusalem

Generalization in RL Compositional Representation Learning Partially Observable RL Reinforcement Learning

Mar 25, 2026

From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments

The remarkable progress of reinforcement learning (RL) is intrinsically tied to the environments used to train and evaluate artificial agents. Moving beyond traditional qualitative reviews, this work presents a large-scale, data-driven empirical investigation into the evolution of RL environments. By programmatically processing a massive corpus of academic literature and rigorously distilling over 2,000 core publications, we propose a quantitative methodology to map the transition from isolated physical simulations to generalist, language-driven foundation agents. Implementing a novel, multi-dimensional taxonomy, we systematically analyze benchmarks against diverse application domains and requisite cognitive capabilities. Our automated semantic and statistical analysis reveals a profound, data-verified paradigm shift: the bifurcation of the field into a "Semantic Prior" ecosystem dominated by Large Language Models (LLMs) and a "Domain-Specific Generalization" ecosystem. Furthermore, we characterize the "cognitive fingerprints" of these distinct domains to uncover the underlying mechanisms of cross-task synergy, multi-domain interference, and zero-shot generalization. Ultimately, this study offers a rigorous, quantitative roadmap for designing the next generation of Embodied Semantic Simulators, bridging the gap between continuous physical control and high-level logical reasoning.

Lijing Luo, Yiben Luo, Alexey Gorbatovski +2

Sun Yat-sen University Shenzhen, China · Yancheng Institute of Technology Yancheng, China · Central University Moscow, Russia +1

RL Benchmarks Reinforcement Learning Generalization in RL RL for LLM Agents Multi-Task RL

Mar 22, 2026

PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost

Post-training for long-horizon agentic tasks has a tension between compute efficiency and generalization. While supervised fine-tuning (SFT) is compute efficient, it often suffers from out-of-domain (OOD) degradation. Conversely, end-to-end reinforcement learning (E2E RL) preserves OOD capabilities, but incurs high compute costs due to many turns of on-policy rollout. We introduce PivotRL, a novel framework that operates on existing SFT trajectories to combine the compute efficiency of SFT with the OOD accuracy of E2E RL. PivotRL relies on two key mechanisms: first, it executes local, on-policy rollouts and filters for pivots: informative intermediate turns where sampled actions exhibit high variance in outcomes; second, it utilizes rewards for functional-equivalent actions rather than demanding strict string matching with the SFT data demonstration. We theoretically show that these mechanisms incentivize strong learning signals with high natural gradient norm, while maximally preserving policy probability ordering on actions unrelated to training tasks. In comparison to standard SFT on identical data, we demonstrate that PivotRL achieves +4.17% higher in-domain accuracy on average across four agentic domains, and +10.04% higher OOD accuracy in non-agentic tasks. Notably, on agentic coding tasks, PivotRL achieves competitive accuracy with E2E RL with 4x fewer rollout turns. PivotRL is adopted by NVIDIA's Nemotron-3-Super-120B-A12B, acting as the workhorse in production-scale agentic post-training.

Junkeun Yi, Damon Mosk-Aoyama, Baihe Huang +9

NVIDIA · UC Berkeley

RL Post-Training RL for LLM Agents Agentic RL Reinforcement Learning Generalization in RL

Mar 18, 2026

Per-Domain Generalizing Policies: On Learning Efficient and Robust Q-Value Functions (Extended Version with Technical Appendix)

Learning per-domain generalizing policies is a key challenge in learning for planning. Standard approaches learn state-value functions represented as graph neural networks using supervised learning on optimal plans generated by a teacher planner. In this work, we advocate for learning Q-value functions instead. Such policies are drastically cheaper to evaluate for a given state, as they need to process only the current state rather than every successor. Surprisingly, vanilla supervised learning of Q-values performs poorly as it does not learn to distinguish between the actions taken and those not taken by the teacher. We address this by using regularization terms that enforce this distinction, resulting in Q-value policies that consistently outperform state-value policies across a range of 10 domains and are competitive with the planner LAMA-first.

Nicola J. Müller, Moritz Oster, Isabel Valera +2

German Research Center for Artificial Intelligence (DFKI), Saarbrücken, Germany · Saarland University, Saarland Informatics Campus, Saarbrücken, Germany · Center for European Research in Trusted Artificial Intelligence (CERTAIN)

Generalization in RL Q-Learning Reinforcement Learning

Mar 16, 2026

ViSA: Visited-State Augmentation for Generalized Goal-Space Contrastive Reinforcement Learning

Goal-Conditioned Reinforcement Learning (GCRL) is a framework for learning a policy that can reach arbitrarily given goals. In particular, Contrastive Reinforcement Learning (CRL) provides a framework for policy updates using an approximation of the value function estimated via contrastive learning, achieving higher sample efficiency compared to conventional methods. However, since CRL treats the visited state as a pseudo-goal during learning, it can accurately estimate the value function only for limited goals. To address this issue, we propose a novel data augmentation approach for CRL called ViSA (Visited-State Augmentation). ViSA consists of two components: 1) generating augmented state samples, with the aim of augmenting hard-to-visit state samples during on-policy exploration, and 2) learning consistent embedding space, which uses an augmented state as auxiliary information to regularize the embedding space by reformulating the objective function of the embedding space based on mutual information. We evaluate ViSA in simulation and real-world robotic tasks and show improved goal-space generalization, which permits accurate value estimation for hard-to-visit goals. Further details can be found on the project page: https://issa-n.github.io/projectPage_ViSA/

Issa Nakamura, Tomoya Yamanokuchi, Yuki Kadokawa +5

I. Nakamura, T. Yamanokuchi, Y. Kadokawa, and T. Matsubara are with the Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Nara, Japan. · J. Qu, S. Otsubo, Y. Susumu, S. Miwa are with the Advanced Technology R&D Center, Mitsubishi Electric Corporation, Hyogo, Japan.

Reinforcement Learning Goal-Conditioned RL Contrastive RL Generalization in RL

Mar 12, 2026

Can RL Improve Generalization of LLM Agents? An Empirical Study

Reinforcement fine-tuning (RFT) has shown promise for training LLM agents to perform multi-turn decision-making based on environment feedback. However, most existing evaluations remain largely in-domain: training and testing are conducted in the same environment or even on the same tasks. In real-world deployment, agents may operate in unseen environments with different background knowledge, observation spaces, and action interfaces. To characterize the generalization profile of RFT under such shifts, we conduct a systematic study along three axes: (1) within-environment generalization across task difficulty, (2) cross-environment transfer to unseen environments, and (3) sequential multi-environment training to quantify transfer and forgetting. Our results show that RFT generalizes well across task difficulty within an environment, but exhibits weaker transfer to unseen environments, which correlates with shifts in both semantic priors and observation/action interfaces. In contrast, sequential training yields promising downstream gains with minimal upstream forgetting, and mixture training across environments improves the overall balance. We further provide detailed analyses and deeper insights, and hope our work helps the community develop and deploy generalizable LLM agents.

Zhiheng Xi, Xin Guo, Jiaqi Liu +11

Fudan University · Shanghai Artificial Intelligence Laboratory · Meituan

LLM Agents RL for LLM Agents RL Fine-Tuning Generalization in RL Continual Learning for LLM Agents Multi-Task RL

Mar 8, 2026

DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration

Learned world models excel at interpolative generalization but fail at extrapolative generalization to novel physical properties. This limitation arises because they learn statistical correlations rather than the environment's underlying generative rules, such as physical invariances and conservation laws. We argue that learning these invariances is key to robust extrapolation. To achieve this, we first introduce Symmetry Exploration, an unsupervised exploration strategy where an agent is intrinsically motivated by a Hamiltonian-based curiosity bonus to actively probe and challenge its understanding of conservation laws, thereby collecting physically informative data. Second, we design a Hamiltonian-based world model that learns from the collected data, using a novel self-supervised contrastive objective to identify the invariant physical state from raw, view-dependent pixel observations. Our framework, DreamSAC, trained on this actively curated data, significantly outperforms state-of-the-art baselines in 3D physics simulations on tasks requiring extrapolation.

Jinzhou Tang, Fan Feng, Minghao Fu +3

UC San Diego · Sun Yat-sen University

World Model Learning World Models Generalization in RL Physics-Informed RL Representation Learning for RL

Mar 8, 2026

Generalization in Online Reinforcement Learning for Mobile Agents

Graphical user interface (GUI)-based mobile agents automate digital tasks on mobile devices by interpreting natural-language instructions and interacting with the screen. While recent methods apply reinforcement learning (RL) to train vision-language-model(VLM) agents in interactive environments with a primary focus on performance, generalization remains underexplored due to the lack of standardized benchmarks and open-source RL systems. In this work, we formalize the problem as a Contextual Markov Decision Process (CMDP) and introduce AndroidWorld-Generalization, a benchmark with three increasingly challenging regimes for evaluating zero-shot generalization to unseen task instances, templates, and applications. We further propose an RL training system that integrates Group Relative Policy Optimization (GRPO) with a scalable rollout collection system, consisting of containerized infrastructure and asynchronous execution % , and error recovery to support reliable and efficient training. Experiments on AndroidWorld-Generalization show that RL enables a 7B-parameter VLM agent to surpass supervised fine-tuning baselines, yielding a 26.1% improvement on unseen instances but only limited gains on unseen templates (15.7%) and apps (8.3%), underscoring the challenges of generalization. As a preliminary step, we demonstrate that few-shot adaptation at test-time improves performance on unseen apps, motivating future research in this direction. To support reproducibility and fair comparison, we open-source the full RL training system, including the environment, task suite, models, prompt configurations, and the underlying infrastructure \footnote{https://github.com/zihuanjiang/AndroidWorld-Generalization}.

Li Gu, Zihuan Jiang, Zhixiang Chi +5

Mila – Québec AI Institute · Concordia University · University of Toronto +3

RL for GUI Agents Mobile GUI Agents Generalization in RL

Mar 6, 2026

Evaluating Generalization Mechanisms in Autonomous Cyber Attack Agents

Autonomous offensive agents often fail to transfer beyond the networks on which they are trained. We isolate a minimal but fundamental shift -- unseen host/subnet IP reassignment in an otherwise fixed enterprise scenario -- and evaluate attacker generalization in the NetSecGame environment. Agents are trained on five IP-range variants and tested on a sixth unseen variant; only the meta-learning agent may adapt at test time. We compare three agent families (traditional RL, adaptation agents, and LLM-based agents) and use action-distribution-based behavioral/XAI analyses to localize failure modes. Some adaptation methods show partial transfer but significant degradation under unseen reassignment, indicating that even address-space changes can break long-horizon attack policies. Under our evaluation protocol and agent-specific assumptions, prompt-driven pretrained LLM agents achieve the highest success on the held-out reassignment, but at the cost of increased inference-time compute, reduced transparency, and practical failure modes such as repetition/invalid-action loops.

Ondřej Lukáš, Jihoon Shin, Emilia Rivas +6

Czech Technical University in Prague (CTU) · University of Texas at El Paso (UTEP) · Universidad Nacional de Cuyo (UNCUYO)

Generalization in RL AI Agent Evaluation LLMs for Cybersecurity

Mar 6, 2026

Synthetic Monitoring Environments for Reinforcement Learning

Reinforcement Learning (RL) lacks benchmarks that enable precise, white-box diagnostics of agent behavior. Current environments often entangle complexity factors and lack ground-truth optimality metrics, making it difficult to isolate why algorithms fail. We introduce Synthetic Monitoring Environments (SMEs), an infinite suite of continuous control tasks. SMEs provide fully configurable task characteristics and known optimal policies. As such, SMEs allow for the exact calculation of instantaneous regret. Their rigorous geometric state space bounds allow for systematic within-distribution (WD) and out-of-distribution (OOD) evaluation. We demonstrate the framework's benefit through multidimensional ablations of PPO, TD3, and SAC, revealing how specific environmental properties - such as action or state space size, reward sparsity and complexity of the optimal policy - impact WD and OOD performance. We thereby show that SMEs offer a standardized, transparent testbed for transitioning RL evaluation from empirical benchmarking toward rigorous scientific analysis.

Leonard Pleiss, Carolin Schmidt, Maximilian Schiffer

Technical University Munich Munich, 80331

RL Benchmarks Reinforcement Learning Generalization in RL Continuous Control

Mar 3, 2026

Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement Learning

Offline meta-reinforcement learning seeks to learn a policy that generalizes to new related tasks online. Context-based methods infer a task representation from transition histories, yet learning an effective task representation without supervision remains challenging. Existing methods relying on contrastive learning learn discriminative task representations, but fail to identify task-specific dynamics, while relying on reconstruction can be insufficient to model long-horizon dependencies, limiting generalization to new tasks. We investigate the impact of temporal consistency in latent space on task representation learning, showing that enforcing multi-step predictions in latent space encourages task representations that are able to capture task-dependent dynamics while preventing representation collapse. We provide theoretical analysis characterizing sources of error in value estimation and show through extensive experiments on MuJoCo, Contextual DeepMind Control, and MetaWorld benchmarks that temporal consistency significantly improves both zero-shot and few-shot generalization.

Mohammadreza Nakheai, Aidan Scannell, Kevin Luck +1

Aalto University · Toyota Research Institute · Vrije Universiteit Amsterdam

Representation Learning Offline RL Representation Learning for RL Meta-Reinforcement Learning Generalization in RL Temporal Consistency+2

Mar 2, 2026

Chain-of-Context Learning: Dynamic Constraint Understanding for Multi-Task VRPs

Multi-task Vehicle Routing Problems (VRPs) aim to minimize routing costs while satisfying diverse constraints. Existing solvers typically adopt a unified reinforcement learning (RL) framework to learn generalizable patterns across tasks. However, they often overlook the constraint and node dynamics during the decision process, making the model fail to accurately react to the current context. To address this limitation, we propose Chain-of-Context Learning (CCL), a novel framework that progressively captures the evolving context to guide fine-grained node adaptation. Specifically, CCL constructs step-wise contextual information via a Relevance-Guided Context Reformulation (RGCR) module, which adaptively prioritizes salient constraints. This context then guides node updates through a Trajectory-Shared Node Re-embedding (TSNR) module, which aggregates shared node features from all trajectories' contexts and uses them to update inputs for the next step. By modeling evolving preferences of the RL agent, CCL captures step-by-step dependencies in sequential decision-making. We evaluate CCL on 48 diverse VRP variants, including 16 in-distribution and 32 out-of-distribution (with unseen constraints) tasks. Experimental results show that CCL performs favorably against the state-of-the-art baselines, achieving the best performance on all in-distribution tasks and the majority of out-of-distribution tasks.

Shuangchun Gui, Suyu Liu, Xuehe Wang +1

School of Computing and Information Systems, Singapore Management University, Singapore · Guangdong Laboratory of AI and Digital Economy, Shenzhen, Guangdong, China · School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, Guangdong, China

RL for Combinatorial Optimization Multi-Task RL Generalization in RL

Feb 28, 2026

Hereditary Geometric Meta-RL: Nonlocal Generalization via Task Symmetries

Meta-Reinforcement Learning (Meta-RL) commonly generalizes via smoothness in the task encoding. While this enables local generalization around each training task, it requires dense coverage of the task space and leaves richer task space structure untapped. In response, we develop a geometric perspective that endows the task space with a "hereditary geometry" induced by the inherent symmetries of the underlying system. Concretely, the agent reuses a policy learned at the train time by transforming states and actions through actions of a Lie group. This converts Meta-RL into symmetry discovery rather than smooth extrapolation, enabling the agent to generalize to wider regions of the task space. We show that when the task space is inherited from the symmetries of the underlying system, the task space embeds into a subgroup of those symmetries whose actions are linearizable, connected, and compact--properties that enable efficient learning and inference at the test time. To learn these structures, we develop a differential symmetry discovery method. This collapses functional invariance constraints and thereby improves numerical stability and sample efficiency over functional approaches. Empirically, on a two-dimensional navigation task, our method efficiently recovers the ground-truth symmetry and generalizes across the entire task space, while a common baseline generalizes only near training tasks.

Paul Nitschke, Shahriar Talebi

P. Nitschke is with the Paulson School Of Engineering And Applied Sciences, Harvard University, Cambridge, US. · S. Talebi is with the UCLA Samueli School of Engineering and Applied Science, University of California, Los Angeles, US.

Symmetry Discovery Meta-Reinforcement Learning Generalization in RL Geometric Representation Learning

Feb 25, 2026

Generalisation of RLHF under Reward Shift and Clipped KL Regularisation

Alignment and adaptation in large language models heavily rely on reinforcement learning from human feedback (RLHF); yet, theoretical understanding of its generalisability remains premature, especially when the learned reward could shift, and the KL control is estimated and clipped. To address this issue, we develop generalisation theory for RLHF that explicitly accounts for (1) reward shift: reward models are trained on preference data from earlier or mixed behaviour policies while RLHF optimises the current policy on its own rollouts; and (2) clipped KL regularisation: the KL regulariser is estimated from sampled log-probability ratios and then clipped for stabilisation, resulting in an error to RLHF. We present generalisation bounds for RLHF, suggesting that the generalisation error stems from a sampling error from prompts and rollouts, a reward shift error, and a KL clipping error. We also discuss special cases of (1) initialising RLHF parameters with a uniform prior over a finite space, and (2) training RLHF by stochastic gradient descent, as an Ornstein-Uhlenbeck process. The theory yields practical implications in (1) optimal KL clipping threshold, and (2) budget allocation in prompts, rollouts, and preference data.

Kenton Tang, Yuzhu Chen, Fengxiang He

University of Edinburgh · University of Science and Technology of China

RL from Human Feedback Generalization in RL KL-Regularized RL

Feb 23, 2026

Sparse Masked Attention Policies for Reliable Generalization

In reinforcement learning, abstraction methods that remove unnecessary information from the observation are commonly used to learn policies which generalize better to unseen tasks. However, these methods often overlook a crucial weakness: the function which extracts the reduced-information representation has unknown generalization ability in unseen observations. In this paper, we address this problem by presenting an information removal method which more reliably generalizes to new states. We accomplish this by using a learned masking function which operates on, and is integrated with, the attention weights within an attention-based policy network. We demonstrate that our method significantly improves policy generalization to unseen tasks in the Procgen benchmark compared to standard PPO and masking approaches.

Caroline Horsch, Laurens Engwegen, Max Weltevrede +2

Department of Intelligent Systems, Delft University of Technology, Delft, Netherlands.

Reinforcement Learning Generalization in RL Representation Learning for RL

Feb 23, 2026

Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent

Humans are highly effective at utilizing prior knowledge to adapt to novel tasks, a capability that standard machine learning models struggle to replicate due to their reliance on task-specific training. Meta-learning overcomes this limitation by allowing models to acquire transferable knowledge from various tasks, enabling rapid adaptation to new challenges with minimal data. This survey provides a rigorous, task-based formalization of meta-learning and meta-reinforcement learning and uses that paradigm to chronicle the landmark algorithms that paved the way for DeepMind's Adaptive Agent, consolidating the essential concepts needed to understand the Adaptive Agent and other generalist approaches.

Björn Hoppmann, Christoph Scholz

Meta-Learning Meta-Reinforcement Learning Generalization in RL

Feb 22, 2026

Robust Exploration in Directed Controller Synthesis via Reinforcement Learning with Soft Mixture-of-Experts

On-the-fly Directed Controller Synthesis (OTF-DCS) mitigates state-space explosion by incrementally exploring the system and relies critically on an exploration policy to guide search efficiently. Recent reinforcement learning (RL) approaches learn such policies and achieve promising zero-shot generalization from small training instances to larger unseen ones. However, a fundamental limitation is anisotropic generalization, where an RL policy exhibits strong performance only in a specific region of the domain-parameter space while remaining fragile elsewhere due to training stochasticity and trajectory-dependent bias. To address this, we propose a Soft Mixture-of-Experts framework that combines multiple RL experts via a prior-confidence gating mechanism and treats these anisotropic behaviors as complementary specializations. The evaluation on the Air Traffic benchmark shows that Soft-MoE substantially expands the solvable parameter space and improves robustness compared to any single expert.

Toshihide Ubukata, Zhiyao Wang, Enhong Mu +2

Waseda University, Tokyo, 169-8050, Japan. · Osaka University, Japan. · Southwest University, China. +1

RL Exploration Generalization in RL Robust RL Mixture of Experts

Feb 18, 2026

Discovering Multiagent Learning Algorithms with Large Language Models

Much of the advancement in Multi-Agent Reinforcement Learning (MARL) for imperfect-information games has historically depended on the manual, iterative refinement of algorithmic baselines. Recently, evolutionary coding agents powered by Large Language Models (LLMs) have emerged as powerful tools to automate this discovery process. In this work, we deploy one of such agentic frameworks, AlphaEvolve, to navigate the design spaces of two distinct game-theoretic paradigms: counterfactual regret minimization (CFR) and policy-space response oracles (PSRO). This automated search yielded two algorithms: Volatility-Adaptive Discounted (VAD-) CFR and Smoothed Hybrid Optimistic Regret (SHOR-) PSRO, which are consistently competitive with state-of-the-art human-designed baselines across an 18-game evaluation suite spanning Poker, Goofspiel, Liar's Dice, Blotto, and Battleship variants. However, because the LLM optimizes for fitness on a specific training set, it often constructs highly synergistic, complex mechanisms tailored to those environments. Through systematic ablation studies, we demonstrate that while these mechanisms are tightly coupled, the true driver of generalization lies in a minimal algorithmic core. By distilling the LLM's discoveries down to their most fundamental principles, we produce two minimal solvers: Warm-started Optimistic Predictive (WOP-)CFR and Projection Matching (PM-)PSRO. These distilled versions achieve superior performance on generalization with greatly reduced structural complexity, providing a clear methodology for using LLMs in algorithmic discovery.

Zun Li, John Schultz, Daniel Hennes +1

Google DeepMind

Counterfactual Regret Minimization Multi-Agent Reinforcement Learning Regret Minimization Generalization in RL Large Language Model-Guided Optimization

Feb 18, 2026

Multi-Agent Reinforcement Learning for V2X Resource Allocation: Disentangling MARL Challenges Through Benchmarking

Radio resource allocation (RRA) is a critical function in cellular vehicle-to-everything (C-V2X) networks, where vehicles must share limited wireless resources to support safety-critical communications. Multi-agent reinforcement learning (MARL) has emerged as a promising approach for this problem. However, key MARL challenges, including non-stationarity, coordination difficulty, large action space, partial observability, and limited robustness and generalization, are often intertwined, making it difficult to assess their individual impact on performance in vehicular environments. Moreover, existing studies primarily focus on developing new algorithms, while systematic benchmarking and comparative analyses remain limited. To address this gap, we formulate C-V2X RRA as a hierarchy of multi-agent interference games that progressively introduce key MARL challenges. Based on this framework, we develop a suite of benchmark learning tasks and construct training and testing datasets from SUMO-generated highway traces with diverse vehicular topologies and interference conditions. Using the proposed benchmark, we evaluate representative MARL algorithms spanning value-based, actor-critic, Independent Learning (IL), and Centralized Training with Decentralized Execution (CTDE) paradigms. The results identify robustness and generalization across diverse vehicular topologies as the dominant challenge among those considered in this work, reducing average normalized return by up to 59 percentage points, and show that, on the most challenging task, the best actor-critic method outperforms the best value-based method by 42%. By revealing the relative strengths and limitations of different MARL paradigms and open-sourcing the code, datasets, and benchmark suite, this work provides a systematic and reproducible foundation for evaluating and advancing MARL algorithms in vehicular networks.

Siyuan Wang, Lei Lei, Pranav Maheshwari +2

College of Engineering, University of Guelph, Guelph, Ontario, Canada · College of Electrical Engineering and Computer Sciences, Ningbo University, Ningbo, 315211, China

RL Benchmarks Reinforcement Learning V2X Communication Wireless Resource Allocation Robust RL Generalization in RL+1

Feb 18, 2026

EnterpriseBench Corecraft: Training Generalizable Agents on High-Fidelity RL Environments

We show that training AI agents on high-fidelity reinforcement learning environments produces capabilities that generalize beyond the training distribution. We introduce CoreCraft, the first environment in EnterpriseBench, Surge AI's suite of agentic RL environments. CoreCraft is a fully operational enterprise simulation of a customer support organization, comprising over 2,500 entities across 14 entity types with 23 unique tools, designed to measure whether AI agents can perform the multi-step, domain-specific work that real jobs demand. Frontier models such as GPT-5.2 and Claude Opus 4.6 solve fewer than 30% of tasks when all expert-authored rubric criteria must be satisfied. Using this environment, we train GLM 4.6 with Group Relative Policy Optimization (GRPO) and adaptive clipping. After a single epoch of training, the model improves from 25.37% to 36.76% task pass rate on held-out evaluation tasks. More importantly, these gains transfer to out-of-distribution benchmarks: +4.5% on BFCL Parallel, +7.4% on Tau2-Bench Retail, and +6.8% on Tool Decathlon (Pass@1). We believe three environment properties are consistent with the observed transfer: task-centric world building that optimizes for diverse, challenging tasks; expert-authored rubrics enabling reliable reward computation; and enterprise workflows that reflect realistic professional patterns. Our results suggest that environment quality, diversity, and realism are key factors enabling generalizable agent capabilities.

Sushant Mehta, Logan Ritchie, Suhaas Garre +3

Surge AI

LLM Agent Training RL for LLM Agents Generalization in RL AI Agent Benchmarks

Feb 17, 2026

Contextual Intelligence The Next Leap for Reinforcement Learning

Reinforcement learning (RL) has produced spectacular results in games, robotics, and continuous control. Yet, despite these successes, learned policies often fail to generalize beyond their training distribution, limiting real-world impact. Recent work on contextual RL (cRL) shows that exposing agents to environment characteristics -- contexts -- can improve zero-shot transfer. So far, the community has treated context as a monolithic, static observable, an approach that constrains the generalization capabilities of RL agents. To achieve contextual intelligence we first propose a novel taxonomy of contexts that separates allogenic (environment-imposed) from autogenic (agent-driven) factors. We identify three fundamental research directions that must be addressed to promote truly contextual intelligence: (1) Learning with heterogeneous contexts to explicitly exploit the taxonomy levels so agents can reason about their influence on the world and vice versa; (2) Multi-time-scale modeling to recognize that allogenic variables evolve slowly or remain static, whereas autogenic variables may change within an episode, potentially requiring different learning mechanisms; (3) Integration of abstract, high-level contexts to incorporate roles, resource & regulatory regimes, uncertainties, and other non-physical descriptors that crucially influence behavior. We envision context as a first-class modeling primitive, empowering agents to reason about who they are, what the world permits, and how both evolve over time. By doing so, we aim to catalyze a new generation of context-aware agents that can be deployed safely and efficiently in the real world.

André Biedenkapp

Albert-Ludwigs-Universität Freiburg, Germany

Contextual RL Zero-Shot RL Reinforcement Learning Generalization in RL Transfer Learning

Jan 30, 2026

PlatoLTL: Scaling LTL-Guided Multi-Task RL

Linear temporal logic (LTL) has emerged as a powerful formalism for specifying structured, temporally extended tasks in multi-task reinforcement learning (RL). However, while existing approaches in LTL-guided multi-task RL demonstrate success in simple environments, they suffer from challenges in representation learning and exploration efficiency when applied to high-dimensional environments with parameterized specifications. We present PlatoLTL, which elevates state-of-the-art methods to address both challenges. We model atomic propositions as instances of atomic predicates and inject task parameters directly into the goal embedding to enable efficient generalization. We also leverage simple priors on closeness to predicate satisfaction to enable and accelerate learning of complex tasks without biasing the optimal policy. We validate our approach on challenging environments including robotic manipulation and multi-drone navigation.

Jacques Cloete, Mathias Jackermeier, Ioannis Havoutis +1

Oxford Robotics Institute University of Oxford Oxford, United Kingdom · Department of Computer Science University of Oxford Oxford, United Kingdom

RL for Robotics Constrained RL Multi-Task RL Generalization in RL Goal-Conditioned RL

Jan 20, 2026

KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning

Pixel-based reinforcement learning agents often fail under purely visual distribution shift even when latent dynamics and rewards are unchanged, but existing benchmarks entangle multiple sources of shift and hinder systematic analysis. We introduce KAGE-Env, a JAX-native 2D platformer that factorizes the observation process into independently controllable visual axes while keeping the underlying control problem fixed. By construction, varying a visual axis affects performance only through the induced state-conditional action distribution of a pixel policy, providing a clean abstraction for visual generalization. Building on this environment, we define KAGE-Bench, a benchmark of six known-axis suites comprising 34 train-evaluation configuration pairs that isolate individual visual shifts. Using a standard PPO-CNN baseline, we observe strong axis-dependent failures, with background and photometric shifts often collapsing success, while agent-appearance shifts are comparatively benign. Several shifts preserve forward motion while breaking task completion, showing that return alone can obscure generalization failures. Finally, the fully vectorized JAX implementation enables up to 33M environment steps per second on a single GPU, enabling fast and reproducible sweeps over visual factors. Code: https://avanturist322.github.io/KAGEBench/.

Egor Cherepanov, Daniil Zelezetsky, Alexey K. Kovalev +1

1AXXX, Moscow, Russia · 2MIRAI, Moscow, Russia

RL Benchmarks Reinforcement Learning Domain Generalization Visual RL Generalization in RL

Dec 24, 2025

Meta-RL with Bayesian Linear Task Models

Deep Bayesian reinforcement learning adapts to unseen tasks by inferring latent transition and reward models, but existing methods typically rely on variational posteriors and evidence lower bounds, introducing approximation error and unstable task representations. We introduce GLiBRL, a deep Bayesian RL framework that combines generalised linear task models with learnable non-linear basis functions. GLiBRL features conjugate Bayesian inference, yielding exact, sequential posterior updates over task parameters and model noise, together with a closed-form marginal likelihood that eliminates variational inference. The update is naturally permutation-invariant, allowing GLiBRL to integrate with both off- and on-policy algorithms. GLiBRL also learns task representation admitting an exact kernel identity, relating distances between task representations to kernel discrepancies over the task contexts. Compared against eight representative or recent meta reinforcement learning methods, GLiBRL achieves the highest aggregate zero-shot test performance on both the MuJoCo locomotion and MetaWorld manipulation benchmarks.

Jingyang You, Hanna Kurniawati

School of Computing Australian National University

Representation Learning Reinforcement Learning Bayesian RL Meta-Reinforcement Learning Generalization in RL Model-Based RL

Jul 21, 2025

RAD: Retrieval High-quality Demonstrations to Enhance Decision-making

Offline reinforcement learning (RL) learns policies from fixed datasets, thereby avoiding costly or unsafe environment interactions. However, its reliance on finite static datasets inherently restricts the ability to generalize beyond the training distribution. Prior solutions based on synthetic data augmentation often fail to generalize to unseen scenarios in the (augmented) dataset. To address these challenges, we propose Retrieval High-quAlity Demonstrations (RAD) for decision-making, which innovatively introduces a retrieval mechanism into offline RL. Specifically, RAD retrieves high-return and reachable states from the offline dataset as target states, and leverages a generative model to generate sub-trajectories conditioned on these targets for planning. Since the targets are high-return states, once the agent reaches such a target, it can continue to obtain high returns by following the associated high-return actions, thereby improving policy generalization. Extensive experiments confirm that RAD achieves competitive or superior performance compared to baselines across diverse benchmarks, validating its effectiveness. Our code is available at https://anonymous.4open.science/r/RAD_0925_1-690E.

Lu Guo, Yixiang Shan, Zhengbang Zhu +5

School of Artificial Intelligence, Jilin University, Changchun, China · School of Computer Science, Shanghai Jiao Tong University, Shanghai, China

Offline RL Generalization in RL

Apr 12, 2025

Towards More Efficient, Robust, Instance-adaptive, and Generalizable Sequential Decision making

The primary goal of my Ph.D. study is to develop provably efficient and practical algorithms for data-driven sequential decision-making under uncertainty. My work focuses on reinforcement learning (RL), multi-armed bandits, and their applications, including recommendation systems, computer networks, video analytics, and large language models (LLMs). Sequential decision-making methods, such as bandits and RL, have demonstrated remarkable success - ranging from outperforming human players in complex games like Atari and Go to advancing robotics, recommendation systems, and fine-tuning LLMs. Despite these successes, many established algorithms rely on idealized models that can fail under model misspecifications or adversarial perturbations, particularly in settings where accurate prior knowledge of the underlying model class is unavailable or where malicious users operate within dynamic systems. These challenges are pervasive in real-world applications, where robust and adaptive solutions are critical. Furthermore, while worst-case guarantees provide theoretical reliability, they often fail to capture instance-dependent performance, which can lead to more efficient and practical solutions. Another key challenge lies in generalizing to new, unseen environments, a crucial requirement for deploying these methods in dynamic and unpredictable settings. To address these limitations, my research aims to develop more efficient, robust, instance-adaptive, and generalizable sequential decision-making algorithms for both reinforcement learning and bandits. Towards this end, I focus on developing more efficient, robust, instance-adaptive, and generalizable for both general reinforcement learning (RL) and bandits.

Zhiyong Wang

Department of Computer Science and Engineering, The Chinese University of Hong Kong

Multi-Armed Bandits Reinforcement Learning Robust Multi-Armed Bandits Robust RL Generalization in RL Data-Efficient Learning

Mar 17, 2025

A Generalist Hanabi Agent

Traditional multi-agent reinforcement learning (MARL) systems can develop cooperative strategies through repeated interactions. However, these systems are unable to perform well on any other setting than the one they have been trained on, and struggle to successfully cooperate with unfamiliar collaborators. This is particularly visible in the Hanabi benchmark, a popular 2-to-5 player cooperative card-game which requires complex reasoning and precise assistance to other agents. Current MARL agents for Hanabi can only learn one specific game-setting (e.g., 2-player games), and play with the same algorithmic agents. This is in stark contrast to humans, who can quickly adjust their strategies to work with unfamiliar partners or situations. In this paper, we introduce Recurrent Replay Relevance Distributed DQN (R3D2), a generalist agent for Hanabi, designed to overcome these limitations. We reformulate the task using text, as language has been shown to improve transfer. We then propose a distributed MARL algorithm that copes with the resulting dynamic observation- and action-space. In doing so, our agent is the first that can play all game settings concurrently, and extend strategies learned from one setting to other ones. As a consequence, our agent also demonstrates the ability to collaborate with different algorithmic agents -- agents that are themselves unable to do so. The implementation code is available at: R3D2-A-Generalist-Hanabi-Agent

Arjun V Sudhakar, Hadi Nekoei, Mathieu Reymond +3

Chandar Research Lab · Mila – Quebec AI Institute · Polytechnique Montréal +4

RL for Game AI Cooperative MARL Generalization in RL Ad Hoc Teamwork Distributed RL

Oct 4, 2024

Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs

In the zero-shot policy transfer (ZSPT) setting for contextual Markov decision processes (CMDP), agents train on a fixed, finite set of contexts and must generalize to new ones. Recent work has demonstrated that training on additional states, even if they are irrelevant for solving the current context, can improve generalization to unseen contexts. In this paper, we demonstrate that training on these states can indeed improve generalization, but can come at a cost of reducing the accuracy of the learned value function, which should hurt generalization. We hypothesize and demonstrate that increasing the agent's coverage by training on these additional states while also increasing the accuracy improves generalization even further. Inspired by this, we propose a simple approach Explore-Go that leverages existing pure exploration strategies in a new way: by introducing a pure exploration phase at the start of each training episode. Unlike previous approaches that apply exploration strategies for the purpose of improving generalization, our approach can be combined with both on- and off-policy algorithms. We demonstrate the effectiveness of Explore-Go when combined with several popular algorithms and show an increase in test-time performance across several generalization benchmarks, even partially observable ones. With this, we hope to provide practitioners with a simple modification that can significantly improve the generalization of their agents.

Max Weltevrede, Caroline Horsch, Matthijs T. J. Spaan +1

Delft University of Technology, Delft, The Netherlands

Reinforcement Learning RL Exploration Transfer Learning Contextual RL Zero-Shot Policy Transfer Policy Learning+2

May 7, 2024

Policy Learning with a Language Bottleneck

Modern AI systems such as self-driving cars and game-playing agents can achieve superhuman performance, but often lack human-like generalization, interpretability, and inter-operability with human users. Inspired by the rich interactions between language and decision-making in humans, we introduce Policy Learning with a Language Bottleneck (PLLB), a framework enabling AI agents to generate linguistic rules that capture the high-level strategies underlying rewarding behaviors. PLLB alternates between a rule generation step guided by language models, and an update step where agents learn new policies guided by rules, even when a rule is insufficient to describe an entire complex policy. Across five diverse tasks, including a two-player signaling game, maze navigation, image reconstruction, and robot grasp planning, we show that PLLB agents are not only able to learn more interpretable and generalizable behaviors, but can also share the learned rules with human users, enabling more effective human-AI coordination. We provide source code for our experiments at https://github.com/meghabyte/bottleneck .

Megha Srivastava, Cedric Colas, Dorsa Sadigh +1

Stanford University · Massachusetts Institute of Technology Inria

Policy Learning LLM-Guided RL Interpretability in RL Generalization in RL Human-AI Interaction