Partially Observable RL

RL: Reinforcement Learning

Ask about this topic

Overview

Partially observable reinforcement learning studies how an agent can make good decisions when it sees only incomplete or noisy clues about the world, as in the POMDP setting. Common approaches estimate a belief over hidden states, plan with that belief or a learned world model, or use recurrent networks and transformers to summarize observation and action histories; some agents also choose actions to gather information. These methods are used in settings such as visual navigation, robotics, medical control, and multi-agent tasks where teammates’ or opponents’ states are hidden. A central tension is how to retain the right information over long histories while keeping learning and planning reliable: memory can help, but inaccurate beliefs, critic errors, and weak evaluation can still limit performance.

Latest papers

CardsList

121 papers20 papers in the last four weeks, up 67% on the four weeks before. 0.1% of all new papers.

May 4, 2026

Closed-Loop CO2 Storage Control With History-Based Reinforcement Learning and Latent Model-Based Adaptation

Closed-loop management of geological CO2 storage requires control policies that adapt to uncertain reservoir behavior while relying on observations that are realistically available during operation. This work formulates CO2 injection and brine-production control as a partially observable sequential decision problem and studies deployable deep reinforcement-learning controllers trained with high-fidelity reservoir simulation. We first compare privileged-state, well-only, history-conditioned, masking-curriculum, and asymmetric teacher-student model-free policies in order to quantify the value of temporal well-response information and training-time privileged simulator states. We then evaluate a latent model-based adaptation pipeline that reuses nominal latent dynamics and retunes controllers under known injector failure, leakage-induced dynamics and reward shift, and compartmentalized reservoir connectivity. The results show that history-conditioned policies recover nearly all of the privileged-state performance while using only deployable well-level information, and that latent model-based retuning outperforms direct model-free retuning under the same scenario-specific real-simulator budget in the abnormal operating cases. The proposed framework therefore provides a simulator-budget-aware alternative to repeated online history matching and re-optimization for closed-loop CO2 storage control.

Sofianos Panagiotis Fotias, Vassilis Gaganis

School of Mining and Metallurgical Engineering, National Technical University of Athens, Athens 157 73, Greece · Institute of Geoenergy, Foundation for Research and Technology, Chania, 73100, Greece

RL ControlLatent Dynamics ModelingPartially Observable RLModel-Based RL
AskPDF
May 1, 2026

Forager: a lightweight testbed for continual learning with partial observability in RL

In continual reinforcement learning (CRL), good performance requires never-ending learning, acting, and exploration in a big, partially observable world. Most CRL experiments have focused on loss of plasticity---the inability to keep learning---in one-off experiments where some unobservable non-stationarity is added to classic fully observable MDPs. Further, these experiments rarely consider the role of partial observability and the importance of CRL agents that use memory or recurrence. One potential reason for this focus on mitigating loss of plasticity without considering partial observability is that many partially-observable CRL environments are prohibitively expensive. In this paper, we introduce Forager, a lightweight partially-observable CRL environment with a constant memory footprint. We provide a set of experiments and sample tasks demonstrating that Forager is challenging for current CRL agents and yet also allows for in-depth study of those agents. We demonstrate that agents exhibit loss of plasticity, proposed mitigations can help, but that most useful is to leverage state construction. We conclude with a variant of Forager that generates an unending stream of new tasks to learn that clearly highlights the limitations of current CRL agents.

Steven Tang, Xinze Xiong, Anna Hakhverdyan +7

Department of Computing Science, University of Alberta, Canada · Alberta Machine Intelligence Institute (Amii) · CIFAR AI Chair

RL BenchmarksLoss of PlasticityReinforcement LearningPartially Observable RLContinual RL
AskPDF
Apr 17, 2026

Active World-Model with 4D-informed Retrieval for Exploration and Awareness

Physical awareness, especially in a large and dynamic environment, is shaped by sensing decisions that determine observability across space, time, and scale, while observations impact the quality of sensing decisions. This loopy information structure makes physical awareness a fundamentally challenging decision problem with partial observations. While in the past decade we have witnessed the unprecedented success of reinforcement learning (RL) in problems with full observability, decision problems with partial observation, such as POMDPs, remain largely open: real-world explorations are excessively costly, while sim-to-real pipeline suffer from unobserved viewpoints. We introduce AW4RE (Active World-model with 4D-informed Retrieval for Exploration), an awareness-centric generative world model that provides a sensor-native surrogate environment for exploring sensing queries. Conditioned on a queried sensing action, AW4RE estimates the action-conditioned observation process. This is done by combining 4D-informed evidence retrieval, action-conditioned geometric support with temporal coherence, and conditional generative completion. Experiments demonstrate that AW4RE produces more grounded and consistent predictions than geometry-aware generative baselines under extreme viewpoint shifts, temporal gaps, and sparse geometric support.

Elaheh Vaezpour, Amirhosein Javadi, Tara Javidi

KavAI · UCSD

Active PerceptionWorld Model LearningPartially Observable RLAction-Conditioned World ModelsActive SensingEmbodied World Models
AskPDF
Apr 15, 2026

InfoChess: A Game of Adversarial Inference and a Laboratory for Quantifiable Information Control

We propose InfoChess, a symmetric adversarial game that elevates competitive information acquisition to the primary objective. There is no piece capture, removing material incentives that would otherwise confound the role of information. Instead, pieces are used to alter visibility. Players are scored on their probabilistic inference of the opponent's king location over the duration of the game. To explore the space of strategies for playing InfoChess, we introduce a hierarchy of heuristic agents defined by increasing levels of opponent modeling, and train a reinforcement learning agent that outperforms these baselines. Leveraging the discrete structure of the game, we analyze gameplay through natural information-theoretic characterizations that include belief entropy, oracle cross entropy, and predictive log score under the action-induced observation channel. These measures disentangle epistemic uncertainty, calibration mismatch, and uncertainty induced by adversarial movement. The design of InfoChess renders it a testbed for studying multi-agent inference under partial observability. We release code for the environment and agents, and a public interface to encourage further study.

Kieran A. Murphy

New Jersey Institute of Technology, Newark, NJ, United States

Imperfect-Information GamesGame-Playing AgentsPartially Observable RL
AskPDF
Apr 10, 2026

Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication

Multi-agent coordination under partial observability requires agents to share complementary private information. While recent methods optimize messages for intermediate objectives (e.g., reconstruction accuracy or mutual information), rather than decision quality, we introduce SeqComm-DFL, unifying the sequential communication with decision-focused learning for task performance. Our approach features value-aware message generation with sequential Stackelberg conditioning: messages maximize receiver decision quality and are generated in priority order, with agents conditioning on their predecessors. The guidance potential determined by their prosocial ordering. We extend Optimal Model Design to communication-augmented world models with QMIX factorization, enabling efficient end-to-end training via implicit differentiation. We prove information-theoretic bounds showing that communication value scales with coordination gaps and establish O(1/T)\mathcal{O}(1/\sqrt{T}) convergence for the bilevel optimization, where TT denotes the number of training iterations. On collaborative healthcare and StarCraft Multi-Agent Challenge (SMAC) benchmarks, SeqComm-DFL achieves four to six times higher cumulative rewards and over 13% win rate improvements, enabling coordination strategies inaccessible under information asymmetry.

Benjamin Amoh, Geoffrey Parker, Wesley Marrero

Thayer School of Engineering, Dartmouth College

Multi-Agent CoordinationMulti-Agent CommunicationCooperative MARLDecision-Focused LearningPartially Observable RL
AskPDF
Apr 9, 2026

PriPG-RL: Privileged Planner-Guided Reinforcement Learning for Partially Observable Systems with Anytime-Feasible MPC

This paper addresses the problem of training a reinforcement learning (RL) policy under partial observability by exploiting a privileged, anytime-feasible planner agent available exclusively during training. We formalize this as a Partially Observable Markov Decision Process (POMDP) in which a planner agent with access to an approximate dynamical model and privileged state information guides a learning agent that observes only a lossy projection of the true state. To realize this framework, we introduce an anytime-feasible Model Predictive Control (MPC) algorithm that serves as the planner agent. For the learning agent, we propose Planner-to-Policy Soft Actor-Critic (P2P-SAC), a method that distills the planner agent's privileged knowledge to mitigate partial observability and thereby improve both sample efficiency and final policy performance. We support this framework with rigorous theoretical analysis. Finally, we validate our approach in simulation using NVIDIA Isaac Lab and successfully deploy it on a real-world Unitree Go2 quadruped navigating complex, obstacle-rich environments.

Mohsen Amiri, Mohsen Amiri, Ali Beikmohammadi +2

The authors are with the Department of Computer and System Science, Stockholm University, 11419 Stockholm, Sweden · The authors are with the School of Mechanical and Material Engineering, Washington State University, Pullman, WA 99164, USA

Partially Observable RLLearning Using Privileged InformationPartially Observable Markov Decision ProcessesModel Predictive Control
AskPDF
Apr 1, 2026

Belief-State RWKV for Reinforcement Learning under Partial Observability

We propose a stronger formulation of RL on top of RWKV-style recurrent sequence models, in which the fixed-size recurrent state is explicitly interpreted as a belief state rather than an opaque hidden vector. Instead of conditioning policy and value on a single summary h_t, we maintain a compact uncertainty-aware state b_t = (μ_t, Σ_t) derived from RWKV-style recurrent statistics and let control depend on both memory and uncertainty. This design targets a key weakness of plain fixed-state policies in partially observed settings: they may store evidence, but not necessarily confidence. We present the method, a theoretical program, and a pilot RL experiment with hidden episode-level observation noise together with a test-time noise sweep. The pilot shows that belief-state policies nearly match the best recurrent baseline overall while slightly improving return on the hardest in-distribution regime and under a held-out noise shift. Additional ablations show that this simple belief readout is currently stronger than two more structured extensions, namely gated memory control and privileged belief targets, underscoring the need for richer benchmarks.

Liu Xiao

Reinforcement LearningPartially Observable RLPartially Observable Markov Decision Processes
AskPDF
Mar 28, 2026

Prediction-Based Markov Violation Scores for Detecting Non-Markovian Observations in Reinforcement Learning

Reinforcement learning algorithms assume that observations satisfy the Markov property, yet real-world sensors frequently violate this assumption through correlated noise, latency, or partial observability. Standard performance metrics conflate Markov breakdowns with other sources of suboptimality, leaving practitioners without tools to detect such violations. This paper introduces a prediction-based Markov Violation Score (MVS) that quantifies non-Markovian structure in observation trajectories. A random forest first removes nonlinear Markov-compliant dynamics; ridge regression then tests whether historical observations reduce prediction error on the residuals beyond what the current observation provides. The resulting score is bounded in [0, 1] and requires no causal graph construction. Evaluation spans six environments (CartPole, Pendulum, Acrobot, HalfCheetah, Hopper, Walker2d), three algorithms (PPO, A2C, SAC), controlled AR(1) noise at six intensity levels, and 10 seeds per condition. In post-hoc detection, 7 of 16 environment-algorithm pairs, primarily high-dimensional locomotion tasks, show significant positive monotonicity between noise intensity and MVS (Spearman rho up to 0.78, confirmed under repeated-measures analysis); under training-time noise, 13 of 16 pairs exhibit statistically significant reward degradation. An inversion phenomenon is documented in low-dimensional environments where the random forest absorbs the noise signal, causing MVS to decrease as true violations grow, a failure mode analyzed in detail. A practical utility experiment demonstrates that MVS correctly identifies partial observability and guides architecture selection, fully recovering performance lost to non-Markovian observations. Source code to reproduce all results is available at https://github.com/NAVEENMN/Markovianes.

Naveen Mysore

Department of Electrical and Computer Engineering, University of California, Santa Barbara, USA

Reinforcement LearningNon-Markovian RLPartially Observable RL
AskPDF
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 RLCompositional Representation LearningPartially Observable RLReinforcement Learning
AskPDF
Mar 26, 2026

Integrating Deep RL and Bayesian Inference for ObjectNav in Mobile Robotics

Autonomous object search is challenging for mobile robots operating in indoor environments due to partial observability, perceptual uncertainty, and the need to trade off exploration and navigation efficiency. Classical probabilistic approaches explicitly represent uncertainty but typically rely on handcrafted action-selection heuristics, while deep reinforcement learning enables adaptive policies but often suffers from slow convergence and limited interpretability. This paper proposes a hybrid object-search framework that integrates Bayesian inference with deep reinforcement learning. The method maintains a spatial belief map over target locations, updated online through Bayesian inference from calibrated object detections, and trains a reinforcement learning policy to select navigation actions directly from this probabilistic representation. The approach is evaluated in realistic indoor simulation using Habitat 3.0 and compared against developed baseline strategies. Across two indoor environments, the proposed method improves success rate while reducing search effort. Overall, the results support the value of combining Bayesian belief estimation with learned action selection to achieve more efficient and reliable objectsearch behavior under partial observability.

João Castelo-Branco, José Santos-Victor, Alexandre Bernardino

Instituto Superior Técnico, Lisbon, Portugal · Institute For Systems and Robotics, Lisbon, Portugal

Object-Goal NavigationRobot NavigationMobile RoboticsPartially Observable RLBayesian RL
AskPDF
Mar 24, 2026

Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning

We investigate neural ordinary and stochastic differential equations (neural ODEs and SDEs) to model stochastic dynamics in fully and partially observed environments within a model-based reinforcement learning (RL) framework. Through a sequence of simulations, we show that neural SDEs more effectively capture the inherent stochasticity of transition dynamics, enabling high-performing policies with improved sample efficiency in challenging scenarios. We leverage neural ODEs and SDEs for efficient policy adaptation to changes in environment dynamics via inverse models, requiring only limited interactions with the new environment. To address partial observability, we introduce a latent SDE model that combines an ODE with a GAN-trained stochastic component in latent space. Policies derived from this model provide a strong baseline, outperforming or matching general model-based and model-free approaches across stochastic continuous-control benchmarks. This work demonstrates the applicability of action-conditional latent SDEs for RL planning in environments with stochastic transitions. Our code is available at: https://github.com/ChaoHan-UoS/NeuralRL

Chao Han, Stefanos Ioannou, Luca Manneschi +4

School of Computer Science, The University of Sheffield, UK · Cancer Research UK National Biomarker Centre, The University of Manchester, UK · School of Chemical, Materials and Biological Engineering, The University of Sheffield, UK +2

Model-Based RLLatent Dynamics ModelingPartially Observable RLNeural ODEsStochastic Differential EquationsNon-Stationary RL
AskPDF
Mar 24, 2026

Safe Decentralized Operation of EV Virtual Power Plant with Limited Network Visibility via Multi-Agent Reinforcement Learning

As power systems advance toward net-zero targets, behind-the-meter renewables are driving rapid growth in distributed energy resources (DERs). Virtual power plants (VPPs) increasingly coordinate these resources to support power distribution network (PDN) operation, with EV charging stations (EVCSs) emerging as a key asset due to their strong impact on local voltages. However, in practice, VPPs must make operational decisions with only partial visibility of PDN states, relying on limited, aggregated information shared by the distribution system operator. This work proposes a safety-enhanced VPP framework for coordinating multiple EVCSs under such realistic information constraints to ensure voltage security while maintaining economic operation. We develop Transformer-assisted Lagrangian Multi-Agent Proximal Policy Optimization (TL-MAPPO), in which EVCS agents learn decentralized charging policies via centralized training with Lagrangian regularization to enforce voltage and demand-satisfaction constraints. A transformer-based embedding layer deployed on each EVCS agent captures temporal correlations among prices, loads, and charging demand to improve decision quality. Experiments on a realistic 33-bus PDN show that the proposed framework reduces voltage violations by approximately 45% and operational costs by approximately 10% compared to representative multi-agent DRL baselines, highlighting its potential for practical VPP deployment.

Chenghao Huang, Jiarong Fan, Weiqing Wang +1

Department of Data Science and AI, Faculty of IT, Monash University, Australia · Monash Energy Institute, Monash University, Australia

Power SystemsDecentralized MARLElectric Vehicle ChargingSafe RLPartially Observable RL
AskPDF
Mar 20, 2026

NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing

Penetration testing - the practice of simulating cyberattacks to identify vulnerabilities - is a complex sequential decision-making task that is inherently partially observable and features large action spaces. Existing RL simulators for this domain are CPU-bound and fixed to narrow scenarios, making it infeasible to train policies that generalize across networks. We present NASimJax, a JAX-native framework that formulates penetration testing as a Contextual POMDP and introduces a network generation pipeline producing structurally diverse, guaranteed-solvable scenarios. The framework reaches up to 80×\times higher environment throughput than previous simulators, enabling experiments on larger networks and tractable hyperparameter searches. We provide PPO and PQN baselines and conduct the first systematic evaluation of unsupervised environment design for penetration testing. We find that Prioritized Level Replay and ACCEL handle dense training distributions better than Domain Randomization, and that training on sparser topologies yields an implicit curriculum that improves generalization - even to topologies denser than those seen during training. A recurrent PPO variant confirms that these distributional findings are not an artifact of feed-forward policies. The code is available at: https://github.com/raphsimon/NASimJax.

Raphael Simon, José Carrasquel, Elli Makdis Antoun +2

CISS Department, Royal Military Academy, Belgium · AI Lab, Vrije Universiteit Brussel, Belgium

RL BenchmarksPartially Observable RLAutomated Penetration Testing
AskPDF
Mar 17, 2026

Communication-Aware Multi-Agent Reinforcement Learning for Decentralized Cooperative UAV Deployment

Autonomous Unmanned Aerial Vehicle (UAV) swarms are increasingly used as rapidly deployable aerial relays and sensing platforms, yet practical deployments must operate under partial observability and intermittent peer-to-peer connectivity. We present a graph-based multi-agent reinforcement learning framework trained under centralized training with decentralized execution (CTDE): a centralized critic and global state are available only during training, while each UAV executes a shared policy using local observations and messages from nearby neighbors. Under restricted communication, neighbor relations are induced by an SNR-threshold connectivity graph. Our architecture encodes local agent state and nearby entities with an agent-entity attention module and aggregates inter-UAV messages with neighbor self-attention over a signal-quality-limited communication graph defined by a channel model. We evaluate the framework on a cooperative relay-deployment task, DroneConnect. Experimental results show that the proposed method achieves an approximately 12% increase in target coverage over MAPPO under restricted communication and partial observability, while remaining competitive with a mixed-integer linear programming (MILP)-based offline upper bound with full node observability.

Enguang Fan, Yifan Chen, Zihan Shan +3

University of Illinois at Urbana-Champaign · Boeing Research and Technology

Cooperative MARLDecentralized MARLMulti-Agent CommunicationPartially Observable RL
AskPDF
Mar 12, 2026

STAIRS-Former: Spatio-Temporal Attention with Interleaved Recursive Structure Transformer for Offline Multi-task Multi-agent Reinforcement Learning

Offline multi-agent reinforcement learning (MARL) with multi-task datasets is challenging due to varying numbers of agents across tasks and the need to generalize to unseen scenarios. Prior works employ transformers with observation tokenization and hierarchical skill learning to address these issues. However, they underutilize the transformer attention mechanism for inter-agent coordination and rely on a single history token, which limits their ability to capture long-horizon temporal dependencies in partially observable MARL settings. In this paper, we propose STAIRS-Former, a transformer architecture augmented with spatial and temporal hierarchies that enables effective attention over critical tokens while capturing long interaction histories. We further introduce token dropout to enhance robustness and generalization across varying agent populations. Extensive experiments on diverse multi-agent benchmarks, including SMAC, SMAC-v2, MPE, and MaMuJoCo, with multi-task datasets demonstrate that STAIRS-Former consistently outperforms prior methods and achieves new state-of-the-art performance.

Jiwon Jeon, Myungsik Cho, Youngchul Sung

School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon 34141, Republic of Korea

Offline MARLTransformer-Based RLMulti-Task RLPartially Observable RL
AskPDF
Mar 11, 2026

UAV-MARL: Multi-Agent Reinforcement Learning for Time-Critical and Dynamic Medical Supply Delivery

Unmanned aerial vehicles (UAVs) are increasingly used to support time-critical medical supply delivery, providing rapid and flexible logistics during emergencies and resource shortages. However, effective deployment of UAV fleets requires coordination mechanisms capable of prioritizing medical requests, allocating limited aerial resources, and adapting delivery schedules under uncertain operational conditions. This paper presents a multi-agent reinforcement learning (MARL) framework for coordinating UAV fleets in stochastic medical delivery scenarios where requests vary in urgency, location, and delivery deadlines. The problem is formulated as a partially observable Markov decision process (POMDP) in which UAV agents maintain awareness of medical delivery demands while having limited visibility of other agents due to communication and localization constraints. The proposed framework employs Proximal Policy Optimization (PPO) as the primary learning algorithm and evaluates several variants, including asynchronous extensions, classical actor--critic methods, and architectural modifications to analyze scalability and performance trade-offs. The model is evaluated using real-world geographic data from selected clinics and hospitals extracted from the OpenStreetMap dataset. The framework provides a decision-support layer that prioritizes medical tasks, reallocates UAV resources in real time, and assists healthcare personnel in managing urgent logistics. Experimental results show that classical PPO achieves superior coordination performance compared to asynchronous and sequential learning strategies, highlighting the potential of reinforcement learning for adaptive and scalable UAV-assisted healthcare logistics.

Islam Guven, Mehmet Parlak

ICTEAM, Université catholique de Louvain Ottignies-Louvain-la-Neuve, Belgium

Multi-Agent CoordinationMulti-Agent Reinforcement LearningAerial RoboticsPartially Observable RLProximal Policy Optimization
AskPDF
Mar 7, 2026

Adversarial Latent-State Training for Robust Policies in Partially Observable Domains

Robustness under latent distribution shift remains challenging in partially observable reinforcement learning. We formalize a focused setting where an adversary selects a hidden initial latent distribution before the episode, termed an adversarial latent-initial-state POMDP. Theoretically, we prove a latent minimax principle, characterize worst-case defender distributions, and derive approximate best-response inequalities with finite-sample concentration bounds that make the optimization and sampling terms explicit. Empirically, using a Battleship benchmark, we demonstrate that targeted exposure to shifted latent distributions reduces average robustness gaps between Spread and Uniform distributions from 10.3 to 3.1 shots at equal budget. Furthermore, iterative best-response training exhibits budget-sensitive behavior that is qualitatively consistent with the theorem-guided diagnostics once one accounts for discounted PPO surrogates and finite-sample noise. Ultimately, we show that for latent-initial-state problems, the framework yields a clean evaluation game and useful theorem-motivated diagnostics while also making clear where implementation-level surrogates and optimization limits enter.

Angad Singh Ahuja

Constrained Image-Synthesis Lab

Robust RLPartially Observable RLDistributionally Robust RLAdversarial Training
AskPDF
Mar 5, 2026

SCoUT: Scalable Communication via Utility-Guided Temporal Grouping in Multi-Agent Reinforcement Learning

Communication can improve coordination in partially observed multi-agent reinforcement learning (MARL), but learning when and who to communicate with requires choosing among many possible sender-recipient pairs, and the effect of any single message on future reward is hard to isolate. We introduce SCoUT (Scalable Communication via Utility-guided Temporal grouping), which addresses both these challenges via temporal and agent abstraction within traditional MARL. During training, SCoUT resamples soft agent groups every KK environment steps (macro-steps) via Gumbel-Softmax; these groups are latent clusters that induce an affinity used as a differentiable prior over recipients. Using the same assignments, a group-aware critic predicts values for each agent group and maps them to per-agent baselines through the same soft assignments, reducing critic complexity and variance. Each agent is trained with a three-headed policy: environment action, send decision, and recipient selection. To obtain precise communication learning signals, we derive counterfactual communication advantages by analytically removing each sender's contribution from the recipient's aggregated messages. This counterfactual computation enables precise credit assignment for both send and recipient-selection decisions. At execution time, all centralized training components are discarded and only the per-agent policy is run, preserving decentralized execution. Project website, videos and code: \hyperlink{https://scout-comm.github.io/}{https://scout-comm.github.io/}

Manav Vora, Gokul Puthumanaillam, Hiroyasu Tsukamoto +1

University of Illinois Urbana-Champaign

Multi-Agent CommunicationMulti-Agent Reinforcement LearningCooperative MARLPartially Observable RL
AskPDF
Mar 4, 2026

When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift

Real-world reinforcement learning systems must operate under distributional drift in their observation streams, yet most policy architectures implicitly assume fully observed and noise-free states. We study robustness of Proximal Policy Optimization (PPO) under temporally persistent sensor failures that induce partial observability and representation shift. To respond to this drift, we augment PPO with temporal sequence models, including Transformers and State Space Models (SSMs), to enable policies to infer missing information from history and maintain performance. Under a stochastic sensor failure process, we prove a high-probability bound on infinite-horizon reward degradation that quantifies how robustness depends on policy smoothness and failure persistence. Empirically, on MuJoCo continuous-control benchmarks with severe sensor dropout, we show Transformer-based sequence policies substantially outperform MLP, RNN, and SSM baselines in robustness, maintaining high returns even when large fractions of sensors are unavailable. These results demonstrate that temporal sequence reasoning provides a principled and practical mechanism for reliable operation under observation drift caused by sensor unreliability.

Kevin Vogt-Lowell, Theodoros Tsiligkaridis, Rodney Lafuente-Mercado +4

MIT Lincoln Laboratory · Harvard · MIT

Robust RLPartially Observable RLProximal Policy OptimizationTransformer-Based RL
AskPDF
Mar 4, 2026

Learning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsampling

Many large-scale platforms and networked control systems have a centralized decision maker interacting with a massive population of agents under strict observability constraints. Motivated by such applications, we study a cooperative Markov game with a global agent and nn homogeneous local agents in a communication-constrained regime, where the global agent only observes a subset of kk local agent states per time step. We propose an alternating learning framework (ALTERNATING-MARL)(\texttt{ALTERNATING-MARL}), where the global agent performs subsampled mean-field QQ-learning against a fixed local policy, and local agents update by optimizing in an induced MDP. We prove that these approximate best-response dynamics converge to an O~(1/k)\widetilde{O}(1/\sqrt{k})-approximate Nash Equilibrium, while separating the sample complexities between the joint state and action spaces. Finally, we validate our results in numerical simulations for multi-robot control.

Emile Anand, Ishani Karmarkar

Georgia Institute of Technology, Atlanta, GA · Stanford University, Palo Alto, CA

Mean-Field MARLReinforcement LearningCooperative MARLMulti-Agent CoordinationPartially Observable RL
AskPDF
Mar 3, 2026

Next Embedding Prediction Makes World Models Stronger

Capturing temporal dependencies is critical for model-based reinforcement learning (MBRL) in partially observable, high-dimensional domains. We introduce NE-Dreamer, a decoder-free MBRL agent that leverages a temporal transformer to predict next-step encoder embeddings from latent state sequences, directly optimizing temporal predictive alignment in representation space. This approach enables NE-Dreamer to learn coherent, predictive state representations without reconstruction losses or auxiliary supervision. On the DeepMind Control Suite, NE-Dreamer matches or exceeds the performance of DreamerV3 and leading decoder-free agents. On a challenging subset of DMLab tasks involving memory and spatial reasoning, NE-Dreamer achieves substantial gains. These results establish next-embedding prediction with temporal transformers as an effective, scalable framework for MBRL in complex, partially observable environments.

George Bredis, Nikita Balagansky, Daniil Gavrilov +1

T-Tech.

Model-Based RLPartially Observable RLRepresentation Learning for RLTransformer-Based RL
AskPDF
Mar 1, 2026

Intent-Context Synergy Reinforcement Learning for Autonomous UAV Decision-Making in Air Combat

Autonomous UAV infiltration in dynamic contested environments remains a significant challenge due to the partially observable nature of threats and the conflicting objectives of mission efficiency versus survivability. Traditional Reinforcement Learning (RL) approaches often suffer from myopic decision-making and struggle to balance these trade-offs in real-time. To address these limitations, this paper proposes an Intent-Context Synergy Reinforcement Learning (ICS-RL) framework. The framework introduces two core innovations: (1) An LSTM-based Intent Prediction Module that forecasts the future trajectories of hostile units, transforming the decision paradigm from reactive avoidance to proactive planning via state augmentation; (2) A Context-Analysis Synergy Mechanism that decomposes the mission into hierarchical sub-tasks (safe cruise, stealth planning, and hostile breakthrough). We design a heterogeneous ensemble of Dueling DQN agents, each specialized in a specific tactical context. A dynamic switching controller based on Max-Advantage values seamlessly integrates these agents, allowing the UAV to adaptively select the optimal policy without hard-coded rules. Extensive simulations demonstrate that ICS-RL significantly outperforms baselines (Standard DDQN) and traditional methods (PSO, Game Theory). The proposed method achieves a mission success rate of 88% and reduces the average exposure frequency to 0.24 per episode, validating its superiority in ensuring robust and stealthy penetration in high-dynamic scenarios.

Jiahao Fu, Feng Yang

National Elite Institute of Engineering,Northwestern Polytechnical University, Xi’an, Shanxi, China · School of Automation, Northwestern Polytechnical University, Xi’an, Shanxi, China

Reinforcement LearningPartially Observable RLDeep Q-LearningHierarchical RL
AskPDF
Feb 24, 2026

On the Structural Non-Preservation of Epistemic Behaviour under Policy Transformation

Reinforcement learning (RL) agents under partial observability often condition actions on internally accumulated information such as memory or inferred latent context. We formalise such information-conditioned interaction patterns as behavioural dependency: variation in action selection with respect to internal information under fixed observations. This induces a probe-relative notion of εε-behavioural equivalence and a within-policy behavioural distance that quantifies probe sensitivity. We establish three structural results. First, the set of policies exhibiting non-trivial behavioural dependency is not closed under convex aggregation. Second, behavioural distance contracts under convex combination. Third, we prove a sufficient local condition under which gradient ascent on a skewed mixture objective decreases behavioural distance when a dominant-mode gradient aligns with the direction of steepest contraction. Minimal bandit and partially observable gridworld experiments provide controlled witnesses of these mechanisms. In the examined settings, behavioural distance decreases under convex aggregation and under continued optimisation with skewed latent priors, and in these experiments it precedes degradation under latent prior shift. These results identify structural conditions under which probe-conditioned behavioural separation is not preserved under common policy transformations.

Alexander Galozy

Center for Applied Intelligent Systems Research, Halmstad University, Sweden

Reinforcement LearningPartially Observable RLPolicy Learning
AskPDF
Feb 23, 2026

Recurrent Structural Policy Gradient for Partially Observable Mean Field Games

Mean Field Games (MFGs) provide a principled framework for modelling interactions in large population systems. However, algorithmic progress has been limited since model-free methods are high variance and exact methods scale poorly. Recent Hybrid Structural Methods (HSMs) reduce variance while maintaining tractability by leveraging low-dimensional individual state and action spaces and known transition dynamics to compute the exact expected return conditioned on Monte Carlo rollouts of common noise. However, HSMs have not been extended to partially observable settings. We propose Recurrent Structural Policy Gradient (RSPG), the first history-aware HSM for MFGs with public partial information. RSPG achieves an order-of-magnitude faster convergence than model-free RL methods while learning history-aware behaviour, unlike current HSMs. To facilitate research into MFGs, we also introduce MFAX, our JAX-based framework for MFGs that supports both analytic and sample-based mean-field updates. MFAX and usage examples can be found at https://clarisse-wibault.github.io/rspg/.

Clarisse Wibault, Johannes Forkel, Sebastian Towers +9

FLAIR, University of Oxford · MLRG, University of Oxford · ifo Institute, LMU Munich +5

Mean Field GamesPolicy Gradient MethodsPartially Observable RL
AskPDF
Feb 21, 2026

In-Context Planning with Latent Temporal Abstractions

Planning-based reinforcement learning for continuous control is bottlenecked by two practical issues: planning at primitive time scales leads to prohibitive branching and long horizons, while real environments are frequently partially observable and exhibit regime shifts that invalidate stationary, fully observed dynamics assumptions. We introduce I-TAP (In-Context Latent Temporal-Abstraction Planner), an offline RL framework that unifies in-context adaptation with online planning in a learned discrete temporal-abstraction space. From offline trajectories, I-TAP learns an observation-conditioned residual-quantization VAE that compresses each observation-macro-action segment into a coarse-to-fine stack of discrete residual tokens, and a temporal Transformer that autoregressively predicts these token stacks from a short recent history. The resulting sequence model acts simultaneously as a context-conditioned prior over abstract actions and a latent dynamics model. At test time, I-TAP performs Monte Carlo Tree Search directly in token space, using short histories for implicit adaptation without gradient update, and decodes selected token stacks into executable actions. Across deterministic MuJoCo, stochastic MuJoCo with per-episode latent dynamics regimes, and high-dimensional Adroit manipulation, including partially observable variants, I-TAP consistently matches or outperforms strong model-free and model-based offline baselines, demonstrating efficient and robust in-context planning under stochastic dynamics and partial observability.

Baiting Luo, Yunuo Zhang, Nathaniel S. Keplinger +3

Vanderbilt University · William & Mary

Model-Based PlanningOffline RLIn-Context RLContextual RLHierarchical RLPartially Observable RL+1
AskPDF
Jan 27, 2026

Model-Free Output Feedback Stabilization via Policy Gradient Methods

Stabilizing a dynamical system is a fundamental problem that serves as a cornerstone for many complex tasks in the field of control systems. The problem becomes challenging when the system model is unknown. Among the Reinforcement Learning (RL) algorithms that have been successfully applied to solve problems pertaining to unknown linear dynamical systems, the policy gradient (PG) method stands out due to its ease of implementation and can solve the problem in a model-free manner. However, most of the existing works on PG methods for unknown linear dynamical systems assume full-state feedback. In this paper, we take a step towards model-free learning for partially observed linear dynamical systems with output feedback and focus on the fundamental stabilization problem of the system. We propose an algorithmic framework that stretches the boundary of PG methods to the problem without global convergence guarantees. We show that by leveraging zeroth-order PG update based on system trajectories and its convergence to stationary points, the proposed algorithms return a stabilizing output feedback policy for discrete-time linear dynamical systems. We also explicitly characterize the sample complexity of our algorithm and verify the effectiveness of the algorithm using numerical examples.

Ankang Zhang, Ming Chi, Xiaoling Wang +1

School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China · College of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, China

Dynamical SystemsPartially Observable RLFeedback ControlPolicy Gradient MethodsModel-Free RL
AskPDF
Oct 3, 2025

To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used privileged expert distillation--which leverages availability of latent state information during training (e.g., from a simulator) to learn and imitate the optimal latent, Markovian policy--to disentangle the task of "learning to see" from "learning to act". While expert distillation is more computationally efficient than RL without latent state information, it also has well-documented failure modes. In this paper--through a simple but instructive theoretical model called the perturbed Block MDP, and controlled experiments on challenging simulated locomotion tasks--we investigate the algorithmic trade-off between privileged expert distillation and standard RL without privileged information. Our main findings are: (1) The trade-off empirically hinges on the stochasticity of the latent dynamics, as theoretically predicted by contrasting approximate decodability with belief contraction in the perturbed Block MDP; and (2) The optimal latent policy is not always the best latent policy to distill. Our results suggest new guidelines for effectively exploiting privileged information, potentially advancing the efficiency of policy learning across many practical partially observable domains.

Yuda Song, Dhruv Rohatgi, Aarti Singh +1

Carnegie Mellon University · Massachusetts Institute of Technology · Aurora Innovation

Partially Observable RLLearning Using Privileged InformationPolicy DistillationMarkov Decision Processes
AskPDF
Sep 24, 2025

Learning Robust Penetration Testing Policies under Partial Observability: A systematic evaluation

Penetration testing, the simulation of cyberattacks to identify security vulnerabilities, presents a sequential decision-making problem well-suited for reinforcement learning (RL) automation. Like many applications of RL to real-world problems, partial observability presents a major challenge, as it invalidates the Markov property present in Markov Decision Processes (MDPs). Partially Observable MDPs require history aggregation or belief state estimation to learn successful policies. We investigate stochastic, partially observable penetration testing scenarios over host networks of varying size, aiming to better reflect real-world complexity through more challenging and representative benchmarks. This approach leads to the development of more robust and transferable policies, which are crucial for ensuring reliable performance across diverse and unpredictable real-world environments. Using vanilla Proximal Policy Optimization (PPO) as a baseline, we compare a selection of PPO-based variants designed to mitigate partial observability, including frame-stacking, augmenting observations with historical information, and employing LSTM or TrXL architectures. We conduct a systematic empirical analysis of these algorithms across different host network sizes. We find that this task greatly benefits from history aggregation. Converging up to four times faster than other approaches. Manual inspection of the learned policies by the algorithms reveals clear distinctions and provides insights that go beyond quantitative results.

Raphael Simon, Pieter Libin, Wim Mees

Cyber Defence Lab, CISS Department Royal Military Academy · AI Lab, Department of Computer Science Vrije Universiteit Brussel

Reinforcement LearningPartially Observable RLAutomated Penetration TestingProximal Policy OptimizationRobust RL
AskPDF
Jul 24, 2025

Quantum Bayesian Networks Can Speed up Reinforcement Learning in Partially Observable Environments

Reinforcement learning (RL) provides a principled framework for decision-making in partially observable environments, which can be modeled as Markov decision processes and compactly represented through dynamic decision Bayesian networks. Recent advances demonstrate that inference on sparse Bayesian networks can be accelerated using quantum rejection sampling combined with amplitude amplification, leading to a computational speedup in estimating acceptance probabilities. Building on this result, we introduce Quantum Bayesian Reinforcement Learning (QBRL), a hybrid quantum-classical look-ahead algorithm for model-based RL in partially observable environments. We present a rigorous, oracle-free time complexity analysis under fault-tolerant assumptions for the quantum device. Unlike standard treatments that assume a black-box oracle, we explicitly specify the inference process, allowing our bounds to more accurately reflect the true computational cost. We show that, for environments whose dynamics form a sparse Bayesian network, horizon-based near-optimal planning can be achieved sub-quadratically faster through quantum-enhanced belief updates. On the other hand, we show that there is no quantum speed-up for environments that are either fully observable, or characterized by Bayesian networks whose maximum in-degree is not small. Furthermore, we present numerical experiments benchmarking QBRL against its classical counterpart on simple yet illustrative decision-making tasks. Our results offer a detailed analysis of how the quantum computational advantage translates into decision-making performance, highlighting that the magnitude of the advantage can vary significantly across different deployment settings.

Gilberto Cunha, Alexandra Ramôa, André Sequeira +2

High-Assurance Software Laboratory (HASLab), INESC TEC, Portugal · Department of Computer Science, University of Minho, Portugal · International Iberian Nanotechnology Laboratory (INL), Portugal

Partially Observable RLBayesian RLQuantum Machine LearningQuantum RLModel-Based RL
AskPDF
Feb 6, 2024

SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems

Recent advancements in multi-agent reinforcement learning (MARL) have opened up vast application prospects, such as swarm control of drones, collaborative manipulation by robotic arms, and multi-target encirclement. However, potential security threats during the MARL deployment need more attention and thorough investigation. Recent research reveals that attackers can rapidly exploit the victim's vulnerabilities, generating adversarial policies that result in the failure of specific tasks. For instance, reducing the winning rate of a superhuman-level Go AI to around 20%. Existing studies predominantly focus on two-player competitive environments, assuming attackers possess complete global state observation. In this study, we unveil, for the first time, the capability of attackers to generate adversarial policies even when restricted to partial observations of the victims in multi-agent competitive environments. Specifically, we propose a novel black-box attack (SUB-PLAY) that incorporates the concept of constructing multiple subgames to mitigate the impact of partial observability and suggests sharing transitions among subpolicies to improve attackers' exploitative ability. Extensive evaluations demonstrate the effectiveness of SUB-PLAY under three typical partial observability limitations. Visualization results indicate that adversarial policies induce significantly different activations of the victims' policy networks. Furthermore, we evaluate three potential defenses aimed at exploring ways to mitigate security threats posed by adversarial policies, providing constructive recommendations for deploying MARL in competitive environments.

Oubo Ma, Yuwen Pu, Linkang Du +5

Zhejiang University · Xi’an Jiaotong University · Laboratory for Big Data and Decision +2

Adversarial AttacksPartially Observable RLBlack-Box Adversarial AttacksMulti-Agent System SecurityMulti-Agent Reinforcement Learning
AskPDF