Planning and acting in partially observable stochastic domains

1998/05/01 by Leslie Pack Kaelbling, Michael L. Littman, Anthony R. Cassandra · 4,161 citations
Computer Science · Mathematics · #AI-based Problem Solving and Planning #Computer science #Controller (irrigation) #Formal Methods in Verification #Logic, Reasoning, and Knowledge #Markov decision process #Markov process #Mathematical optimization #Mathematics #Observable #Partially observable Markov decision process #Work (physics)

paper · pdf · doi:10.1016/s0004-3702(98)00023-x

published in Artificial Intelligence 101(1-2), 99-134 (Elsevier BV)

openalex publication_date 1998/05/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Citations

• Fast planning through planning graph analysis
• A tutorial on hidden Markov models and selected applications in speech recognition

Cited by

• A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress
• Same World, Differently Given: History-Dependent Perceptual Reorganization in Artificial Agents
• TRW: TRACE-RealWorld---An Auditable Consistency Contract for World Models as Materialized Views
• Adaptive Undulatory Locomotion of Snake-like Robots in Dynamic Viscous Environments via Deep Reinforcement Learning
• Cycles of Discourse, Speech Dysfluency, and Active Inference
• Pretraining Recurrent Networks without Recurrence
• Modeling the Development of Cellular Exhaustion and Tumor-Immune Stalemate
• Dreamer-CPC: Message Learning with World Models for Decentralized Multi-agent Reinforcement Learning
• AgentJet: A Distributed Swarm Training Framework for Agentic Reinforcement Learning
• Breaking Feedback-Blindness: Utility-Augmented Transformer for Sequential Decision Making
• A Hardware-oriented Approach for Efficient Bayesian Inference Computation and Deployment
• Generalised Bellman recurrence and three dualities in sequential decision-making
• Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability
• Toward Learning POMDPs Beyond Full-Rank Actions and State Observability
• Reward-Driven LLM Agent Workflows: Synthesizing POMDP Routing and Self-Correction for Autonomous Decision-Making
• RobustVLA: On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
• Expected Free Energy as Belief-Dependent Utility for rho-POMDPs
• Beyond Tracking or Shortcut: Composition-Bounded Predictive States in Poker Autoregressive Models
• Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents
• Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers
• Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies
• TALES: Text Adventure Learning Environment Suite
• QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?
• Partially Observable Markov Decision Processes (POMDPs) and Robotics
• Self-play for Data Efficient Language Acquisition
• Meta reinforcement learning as task inference
• Reinforcement Learning via Self-Distillation
• Assisted Perception: Optimizing Observations to Communicate State
• Heterogeneity in Multi-Agent Reinforcement Learning
• Environmental benefits of enhanced surveillance technology on airport departure operations
• How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?
• Active inference and agency: optimal control without cost functions
• Learning Optimal Decision Making for an Industrial Truck Unloading Robot using Minimal Simulator Runs
• Batch Belief Trees for Motion Planning Under Uncertainty
• Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning
• Active Learning for Autonomous Intelligent Agents: Exploration, Curiosity, and Interaction
• POMP: Pomcp-based Online Motion Planning for active visual search in indoor environments
• Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programming
• Agentic AI in medicine: architectures, applications, evaluation, and challenges for clinical translation
• MEMENTO: Memory-Guided Memetic Code-as-Policy Evolution
• What Can Be Enforced? A Theory of Certified Runtime Safety for Tool-Using Agents
• PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environments
• Variational Neural Belief Parameterizations for Robust Dexterous Grasping under Multimodal Uncertainty
• RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic
• Generalised Linear Models in Deep Bayesian RL with Learnable Basis Functions
• Cruising the Spectrum: Joint Spectrum Mobility and Antenna Array Management for Mobile (cm/mm)Wave Connectivity
• Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments
• LLM-based Few-Shot Early Rumor Detection with Imitation Agent
• Bounty Hunter: Autonomous, Comprehensive Emulation of Multi-Faceted Adversaries
• Efficient Online Learning for Optimizing Value of Information: Theory and Application to Interactive Troubleshooting
• Learning to Track Dynamic Targets in Partially Known Environments
• Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning
• Dynamic Homophily with Imperfect Recall: Modeling Resilience in Adversarial Networks
• B-ActiveSEAL: Scalable Uncertainty-Aware Active Exploration with Tightly Coupled Localization-Mapping
• Learning Finite-State Controllers for Partially Observable Environments
• AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management
• A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms
• On Learning to Think: Algorithmic Information Theory for Novel\n Combinations of Reinforcement Learning Controllers and Recurrent Neural World\n Models
• Reinforcement Learning for Monetary Policy Under Macroeconomic Uncertainty: Analyzing Tabular and Function Approximation Methods
• Elephants Don’t Pack Groceries: Robot Task Planning for Low Entropy Belief States
• Collaborative Causal Sensemaking: Closing the Complementarity Gap in Human-AI Decision Support
• Quantifying Memory Use in Reinforcement Learning with Temporal Range
• Exploiting Causality for Selective Belief Filtering in Dynamic Bayesian Networks (Extended Abstract)
• Termination Analysis of Probabilistic Programs through Positivstellensatz's
• Meta-Learning Multi-armed Bandits for Beam Tracking in 5G and 6G Networks
• Orbitofrontal Cortex as a Cognitive Map of Task Space
• Risk-Aware Reasoning for Autonomous Vehicles
• POrTAL: Plan-Orchestrated Tree Assembly for Lookahead
• Inference-Based Strategy Alignment for General-Sum Differential Games
• From monoliths to modules: Decomposing transducers for efficient world modelling
• Deep Learning in Neural Networks: An Overview
• Forecasting in Offline Reinforcement Learning for Non-stationary Environments
• Real-World Reinforcement Learning of Active Perception Behaviors
• Symmetries at the origin of hierarchical emergence
• Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with\n Latent Confounders
• From CAD to POMDP: Probabilistic Planning for Robotic Disassembly of End-of-Life Products
• HAVEN: Hierarchical Adversary-aware Visibility-Enabled Navigation with Cover Utilization using Deep Transformer Q-Networks
• Fault-Tolerant MARL for CAVs under Observation Perturbations for Highway On-Ramp Merging
• Automated Generation of MDPs Using Logic Programming and LLMs for Robotic Applications
• A Computable Game-Theoretic Framework for Multi-Agent Theory of Mind
• POMDP-Based Routing for DTNs with Partial Knowledge and Dependent Failures
• Learning Massively Multitask World Models for Continuous Control
• The Complexity of Decentralized Control of Markov Decision Processes
• MARL-CC: A Mathematical Framework forMulti-Agent Reinforcement Learning in ConnectedAutonomous Vehicles: Addressing Nonlinearity,Partial Observability, and Credit Assignment forOptimal Control
• Solving POMDPs by Searching the Space of Finite Policies
• SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent
• Revealing POMDPs: Qualitative and Quantitative Analysis for Parity Objectives
• DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPs
• More Than Irrational: Modeling Belief-Biased Agents
• VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
• Reinforcement Learning for Charging Optimization of Inhomogeneous Dicke Quantum Batteries
• Graph Neural Networks, Deep Reinforcement Learning and Probabilistic Topic Modeling for Strategic Multiagent Settings
• CoRL-MPPI: Enhancing MPPI With Learnable Behaviours For Efficient And Provably-Safe Multi-Robot Collision Avoidance
• UAV-Assisted Resilience in 6G and Beyond Network Energy Saving: A Multi-Agent DRL Approach
• Learning to Focus: Prioritizing Informative Histories with Structured Attention Mechanisms in Partially Observable Reinforcement Learning
• Next-Latent Prediction Transformers Learn Compact World Models
• Partially observable Markov decision processes for spoken dialog systems
• Learning Interactive World Model for Object-Centric Reinforcement Learning
• Challenges in Credit Assignment for Multi-Agent Reinforcement Learning in Open Agent Systems
• Vectorized Online POMDP Planning
• Graph-Enhanced Policy Optimization in LLM Agent Training
• Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models
• Completion ≠ Collaboration: Scaling Collaborative Effort with Agents
• Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics
• Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions
• Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation
• Hidden Incentives for Auto-Induced Distributional Shift
• Efficient Inference in Markov Control Problems
• Ecological Semantics: Programming Environments for Situated Language Understanding
• A Tutorial on Sparse Gaussian Processes and Variational Inference
• Collapsing Bandits and Their Application to Public Health Interventions
• Spectrum Exploration and Exploitation for Cognitive Radio: Recent Advances
• INVIGORATE: Interactive Visual Grounding and Grasping in Clutter
• Tensor Decomposition for Multi-agent Predictive State Representation
• Online Learning and Planning in Partially Observable Domains without Prior Knowledge
• Robust Asymmetric Learning in POMDPs
• Integrating Media Selection and Media Effects Using Decision Theory
• Partially Observable Markov Decision Process Modelling for Assessing Hierarchies
• Assurance-Scoped Reliability for Agentic Networks: Capturing the State That Matters
• Learning Backward Transport for Source Localization
• A tutorial on partially observable Markov decision processes
• Efficient Learning and Planning with Compressed Predictive States
• Probabilistic Reasoning about Actions in Nonmonotonic Causal Theories
• Perception-Prediction-Reaction Agents for Deep Reinforcement Learning
• Learning to Gather Information via Imitation
• DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback
• Neural Co-state Policies: Structuring Hidden States in Recurrent Reinforcement Learning
• Scale-invariant temporal history (SITH): optimal slicing of the past in an uncertain world
• Scalable Planning and Learning for Multiagent POMDPs: Extended Version
• Learning Latent Representations to Influence Multi-Agent Interaction
• Shaping Belief States with Generative Environment Models for RL
• Minimal Computational Preconditions for Subjective Perspective in Artificial Agents
• An output-sensitive algorithm for multi-parametric LCPs with sufficient matrices
• Monopoly Deal: A Benchmark Environment for Bounded One-Sided Response Games
• Memory-based control with recurrent neural networks
• Multi-Task Reinforcement Learning with Context-based Representations
• Multi-Environment POMDPs: Discrete Model Uncertainty Under Partial Observability
• Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and Navigation
• The Formalism-Implementation Gap in Reinforcement Learning Research
• HRM-Agent: Training a recurrent reasoning model in dynamic environments using reinforcement learning
• Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial Observability
• Enhancing Tactile-based Reinforcement Learning for Robotic Control
• ESCORT: Efficient Stein-variational and Sliced Consistency-Optimized Temporal Belief Representation for POMDPs
• Reinforcement Learning and Consumption-Savings Behavior
• Many Agent Reinforcement Learning Under Partial Observability
• Reward-Free Attacks in Multi-Agent Reinforcement Learning
• RLAF: Reinforcement Learning from Automaton Feedback
• Active Measuring in Reinforcement Learning With Delayed Negative Effects
• Sparse Stochastic Finite-State Controllers for POMDPs
• GammaZero: Learning To Guide POMDP Belief Space Search With Graph Representations
• Reducing Belief Deviation in Reinforcement Learning for Active Reasoning
• Diffusion Models for Reinforcement Learning: Foundations, Taxonomy, and Development
• A Flexible Multi-Agent Deep Reinforcement Learning Framework for Dynamic Routing and Scheduling of Latency-Critical Services
• MatterDoor: Sampling Zero-shot Spatio-semantic Priors using Generative Models
• Reinforcement Learning with Action-Triggered Observations
• Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learning
• Termination of Nondeterministic Recursive Probabilistic Programs
• Qualitative MDPs and POMDPs: An Order-Of-Magnitude Approximation
• Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks
• Active Learning for UAV-based Semantic Mapping
• SoK: Measuring What Matters for Closed-Loop Security Agents
• Combining Deep Reinforcement Learning and Search for Imperfect-Information Games
• ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context
• The Assistive Multi-Armed Bandit
• Neural Bayesian Filtering
• Monte Carlo Motion Planning for Robot Trajectory Optimization Under Uncertainty
• MAGIC-MASK: Multi-Agent Guided Inter-Agent Collaboration with Mask-Based Explainability for Reinforcement Learning
• Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access
• Kinodynamic Motion Planning for Mobile Robot Navigation across Inconsistent World Models
• Adversarial Reinforcement Learning Framework for ESP Cheater Simulation
• ByteSized32Refactored: Towards an Extensible Interactive Text Games Corpus for LLM World Modeling and Evaluation
• Reinforcement Learning in Partially Observable Markov Decision Processes using Hybrid Probabilistic Logic Programs
• Predicting individual learning trajectories in zebrafish via the free-energy principle
• Partially Observed Structural Causal Models
• MDP modeling for multi-stage stochastic programs
• When Can AI Models Explain Learning? Validity Criteria for AI as Cognitive Models in Education
• Toward a Computational Phenomenology of Meditative Deconstruction: “Letting Go” and the Deconstruction of Experience With Active Inference
• On Optimal Control of Discounted Cost Infinite-Horizon Markov Decision Processes Under Local State Information Structures
• DemoGrasp: Universal Dexterous Grasping from a Single Demonstration
• Model-Based Reinforcement Learning under Random Observation Delays
• Leaf it to renewal: Improved predictive maintenance policies via renewal theory and decision trees
• Learning to Lead Themselves: Agentic AI in MAS using MARL
• Learning Robust Penetration Testing Policies under Partial Observability: A systematic evaluation
• Branching out: Prognostics-Based Replacement Policies for Series Systems
• On the Importance of Multistability for Horizon Generalization in Reinforcement Learning
• Self-Modification of Policy and Utility Function in Rational Agents
• The Topological Trouble With Transformers
• Probing Dec-POMDP Reasoning in Cooperative MARL
• What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty
• Robust Reinforcement Learning in POMDPs with Incomplete and Noisy Observations
• Using Indirect Encoding of Multiple Brains to Produce Multimodal Behavior
• Prepare Before You Act: Learning From Humans to Rearrange Initial States
• I-FailSense: Towards General Robotic Failure Detection with Vision-Language Models
• GUI-ReWalk: Massive Data Generation for GUI Agent via Stochastic Exploration and Intent-Aware Reasoning
• A Formal Analysis and Taxonomy of Task Allocation in Multi-Robot Systems
• Model-Based Bayesian Reinforcement Learning in Large Structured Domains
• Robust feedback motion planning via contraction theory
• Compositional shield synthesis for safe reinforcement learning in partial observability
• TextWorld: A Learning Environment for Text-based Games
• Solving the Min-Max Multiple Traveling Salesmen Problem via Learning-Based Path Generation and Optimal Splitting
• Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning
• Enhancing Generalization in Vision-Language-Action Models by Preserving Pretrained Representations
• Real-time reinforcement learning for turbulent state-dependent control in a bluff-body wake
• WebSight: A Vision-First Architecture for Robust Web Agents
• Information-Theoretic Methods for Planning and Learning in Partially Observable Markov Decision Processes
• Optimal Immunization Policy Using Dynamic Programming
• Instance based Generalization in Reinforcement Learning
• A coalgebraic perspective on predictive processing
• A Markov Decision Process Model for Intrusion Tolerance Problems
• Language (Re)modelling: Towards Embodied Language Understanding
• Towards bridging the gap: Systematic sim-to-real transfer for diverse legged robots
• Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation
• Planning under Uncertainty to Goal Distributions
• Tracking Drift-Plus-Penalty: Utility Maximization for Partially Observable and Controllable Networks
• Neural Recursive Belief States in Multi-Agent Reinforcement Learning
• Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-RL
• Disentangled Multi-Context Meta-Learning: Unlocking robust and Generalized Task Learning
• Online reinforcement learning with sparse rewards through an active inference capsule
• Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning
• Recurrent Off-policy Baselines for Memory-based Continuous Control
• NiceWebRL: a Python library for human subject experiments with reinforcement learning environments
• Attention on flow control: transformer-based reinforcement learning for lift regulation in highly disturbed flows
• AS2FM: Enabling Statistical Model Checking of ROS 2 Systems for Robust Autonomy
• Language and Experience: A Computational Model of Social Learning in Complex Tasks
• Goals and the Structure of Experience
• When is Particle Filtering Efficient for Planning in Partially Observed Linear Dynamical Systems?
• Decoupling Exploration and Exploitation for Meta-Reinforcement Learning\n without Sacrifices
• Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving
• SACBP: Belief Space Planning for Continuous-Time Dynamical Systems via Stochastic Sequential Action Control
• Belief-Conditioned One-Step Diffusion: Real-Time Trajectory Planning with Just-Enough Sensing
• Counting to Explore and Generalize in Text-based Games
• Posterior Sampling for Large Scale Reinforcement Learning
• Simulating Autonomous Driving in Massive Mixed Urban Traffic
• FHHOP: A Factored Hybrid Heuristic Online Planning Algorithm for Large POMDPs
• Timeline-based planning: Expressiveness and Complexity
• Robust Remote Reinforcement Learning over Unreliable Communication Channels using Homomorphic State Encoding
• ROLL: Visual Self-Supervised Reinforcement Learning with Object Reasoning
• In-Context Reinforcement Learning via Communicative World Models
• Synthetic POMDPs to Challenge Memory-Augmented RL: Memory Demand Structure Modeling
• Exploiting Agent and Type Independence in Collaborative Graphical Bayesian Games
• Fast reinforcement learning for decentralized MAC optimization
• Probabilistic Planning by Probabilistic Programming
• Transfer Learning Across Patient Variations with Hidden Parameter Markov Decision Processes
• PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning
• Recurrent Value Functions
• Inferring Reward Machines and Transition Machines from Partially Observable Markov Decision Processes
• Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning
• A Bayesian Approach to Identifying Representational Errors
• Benchmarking Partial Observability in Reinforcement Learning with a Suite of Memory-Improvable Domains
• Learning from Humans as an I-POMDP
• Common Information based Approximate State Representations in Multi-Agent Reinforcement Learning
• Planning for Decentralized Control of Multiple Robots Under Uncertainty
• Augmenting Knowledge through Statistical, Goal-oriented Human-Robot Dialog
• Multi-Agent Belief Sharing through Autonomous Hierarchical Multi-Level Clustering
• Variational Recurrent Models for Solving Partially Observable Control Tasks
• Hybrid quantum-classical algorithm for near-optimal planning in POMDPs
• Learning the Preferences of Ignorant, Inconsistent Agents
• POMDP-lite for Robust Robot Planning under Uncertainty
• Remembering the Markov Property in Cooperative MARL
• EPSILON: An Efficient Planning System for Automated Vehicles in Highly Interactive Environments
• Myopic Bounds for Optimal Policy of POMDPs: An extension of Lovejoy's structural results
• Framing Human-Robot Task Communication as a POMDP
• Learning State-Tracking from Code Using Linear RNNs
• Concentration-Bound Analysis for Probabilistic Programs and Probabilistic Recurrence Relations
• Grounding Hierarchical Reinforcement Learning Models for Knowledge Transfer
• A Framework for Decision-Theoretic Planning I: Combining the Situation Calculus, Conditional Plans, Probability and Utility
• Reinforcement Learning for Strategic Recommendations
• Offline RL With Resource Constrained Online Deployment
• MELD: Meta-Reinforcement Learning from Images via Latent State Models
• Assessing Adaptive World Models in Machines with Novel Games
• Incentive Decision Processes
• Funnel Libraries for Real-Time Robust Feedback Motion Planning
• Shared Autonomy via Hindsight Optimization for Teleoperation and Teaming
• Partially Observable Reference Policy Programming: Solving POMDPs Sans Numerical Optimisation
• FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making
• Toward Large-Scale Agent Guidance in an Urban Taxi Service
• Decision-Theoretic Coordination and Control for Active Multi-Camera Surveillance in Uncertain, Partially Observable Environments
• Bayesian Reinforcement Learning: A Survey
• An informative path planning framework for UAV-based terrain monitoring
• Learning Belief Representations for Imitation Learning in POMDPs
• Link Prediction using Embedded Knowledge Graphs
• Forward and Backward Simulations for Partially Observable Probability
• A Geometric Perspective on Self-Supervised Policy Adaptation
• Bounded Policy Synthesis for POMDPs with Safe-Reachability Objectives
• Probabilistic Loss and its Online Characterization for Simplified Decision Making Under Uncertainty
• A Survey on Reinforcement Learning Methods in Character Animation
• Bayesian Nonparametric Feature and Policy Learning for Decision-Making
• Attention-based Learning for 3D Informative Path Planning
• Robust Active Perception via Data-association aware Belief Space\n planning
• Re4MPC: Reactive Nonlinear MPC for Multi-model Motion Planning via Deep Reinforcement Learning
• MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations
• Solving POMDPs by Searching in Policy Space
• Learning Adaptive Exploration Strategies in Dynamic Environments Through Informed Policy Regularization
• Reinforcement Learning using Guided Observability
• Combining Offline Models and Online Monte-Carlo Tree Search for Planning from Scratch
• Deep Learning based Urban Vehicle Trajectory Analytics
• POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learning
• A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity
• Distributed Constraint Problems for Utilitarian Agents with Privacy Concerns, Recast as POMDPs
• Memory Allocation in Resource-Constrained Reinforcement Learning
• Learning Causal State Representations of Partially Observable Environments
• A Tour of Reinforcement Learning: The View from Continuous Control
• Control Synthesis in Partially Observable Environments for Complex Perception-Related Objectives
• Belief dynamics extraction
• Monte Carlo Bayesian Reinforcement Learning
• Apprenticeship Learning for Model Parameters of Partially Observable Environments
• Single Episode Policy Transfer in Reinforcement Learning
• A Markov Decision Process Analysis of the Cold Start Problem in Bayesian Information Filtering
• Inverse Reinforcement Learning in Swarm Systems
• Deep Reinforcement Learning amidst Lifelong Non-Stationarity
• Balancing Performance and Human Autonomy with Implicit Guidance Agent
• Ego-centric Learning of Communicative World Models for Autonomous Driving
• Language-Informed Synthesis of Rational Agent Models for Grounded Theory-of-Mind Reasoning On-The-Fly
• Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge
• Spatial Language Understanding for Object Search in Partially Observed City-scale Environments
• Stochastic Shortest Path with Energy Constraints in POMDPs
• Zero-Shot Reinforcement Learning Under Partial Observability
• AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions
• Active Digital Twins via Active Inference
• Individual vs. Joint Perception: a Pragmatic Model of Pointing as Communicative Smithian Helping
• Off-Policy Evaluation in Partially Observed Markov Decision Processes under Sequential Ignorability
• Partially Observable Markov Decision Processes with Behavioral Norms
• EgoMap: Projective mapping and structured egocentric memory for Deep RL
• Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps
• Optimality and robustness in path-planning under initial uncertainty
• Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control
• The Complexity of Decentralized Control of Markov Decision Processes
• Internet Congestion Control via Deep Reinforcement Learning
• GRIP: Generative Robust Inference and Perception for Semantic Robot Manipulation in Adversarial Environments
• Neuro-Symbolic Reinforcement Learning with First-Order Logic
• New Approaches for Almost-Sure Termination of Probabilistic Programs
• Distributed Estimation using Bayesian Consensus Filtering
• Multi-agent Bayesian Deep Reinforcement Learning for Microgrid Energy Management under Communication Failures
• Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens
• A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search
• WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planning
• Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation
• Multi-Agent Decentralized Belief Propagation on Graphs
• An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare
• Interactive Language Learning by Question Answering
• Temporal Difference Variational Auto-Encoder
• Deep reinforcement learning driven inspection and maintenance planning under incomplete information and constraints
• Identification of Unexpected Decisions in Partially Observable Monte-Carlo Planning: a Rule-Based Approach
• Non-Gaussian SLAP: Simultaneous Localization and Planning Under Non-Gaussian Uncertainty in Static and Dynamic Environments
• Graph Convolutional Memory using Topological Priors
• Policy-contingent abstraction for robust robot control
• Learning Symbolic Persistent Macro-Actions for POMDP Solving Over Time
• Minimum-Latency FEC Design with Delayed Feedback: Mathematical Modeling and Efficient Algorithms
• POMDPs in Continuous Time and Discrete Spaces
• SAVOR: Skill Affordance Learning from Visuo-Haptic Perception for Robot-Assisted Bite Acquisition
• AI-Native Brand Identity: From Visual Recognition to Cryptographic Verification
• Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs
• Descriptive History Representations: Learning Representations by Answering Questions
• Improving Generalization in Meta-RL with Imaginary Tasks from Latent\n Dynamics Mixture
• Data-assimilated model-informed reinforcement learning
• A Scalable Method for Solving High-Dimensional Continuous POMDPs Using Local Approximation
• Reinforcement learning approach for robustness analysis of complex networks with incomplete information
• Sparse Imagination for Efficient Visual World Model Planning
• Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner
• Optimistic critics can empower small actors
• DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning
• Reinforcement Learning with Temporal Logic Constraints for Partially-Observable Markov Decision Processes
• Implications of Human Irrationality for Reinforcement Learning
• Counterfactual equivalence for POMDPs, and underlying deterministic environments
• Lazy Heuristic Search for Solving POMDPs with Expensive-to-Compute Belief Transitions
• Variational Inference for Data-Efficient Model Learning in POMDPs
• A Convolution and Attention Based Encoder for Reinforcement Learning under Partial Observability
• A Dynamic Reliability-Aware Service Placement for Network Function Virtualization (NFV)
• Oryx: a Scalable Sequence Model for Many-Agent Coordination in Offline MARL
• Lifted Forward Planning in Relational Factored Markov Decision Processes with Concurrent Actions
• iCORPP: Interleaved Commonsense Reasoning and Probabilistic Planning on Robots
• A Survey of Knowledge-based Sequential Decision Making under Uncertainty
• Embodied AI with Foundation Models for Mobile Service Robots: A Systematic Review
• Situationally-Aware Dynamics Learning
• Large Language Models for Planning: A Comprehensive and Systematic Survey
• State Entropy Maximization with Random Encoders for Efficient Exploration
• Deep Active Inference Agents for Delayed and Long-Horizon Environments
• Learning and Reasoning for Robot Sequential Decision Making under Uncertainty
• A Theoretical Connection Between Statistical Physics and Reinforcement Learning
• The Cell Must Go On: Agar.io for Continual Reinforcement Learning
• ChainVLA: Chaining Vision-Language-Action Queries through a Unified Execution State for Long-Horizon Manipulation
• Bayesian Policy Optimization for Model Uncertainty
• Search in Imperfect Information Games
• What is Going on Inside Recurrent Meta Reinforcement Learning Agents?
• Enter the Void - Planning to Seek Entropy When Reward is Scarce
• Sequential Monte Carlo for Policy Optimization in Continuous POMDPs
• Guided Policy Optimization under Partial Observability
• ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection
• Vid2World: Crafting Video Diffusion Models to Interactive World Models
• Control of Probabilistic Systems under Dynamic, Partially Known Environments with Temporal Logic Specifications
• Rethinking System Health Management
• The Traitors: Deception and Trust in Multi-Agent Language Model Simulations
• MTIL: Encoding Full History with Mamba for Temporal Imitation Learning
• Behavior Synthesis via Contact-Aware Fisher Information Maximization
• Hierarchical Reinforcement Learning as a Model of Human Task Interleaving
• Internal State Estimation in Groups via Active Information Gathering
• Robust Finite-Memory Policy Gradients for Hidden-Model POMDPs
• Distilling Realizable Students from Unrealizable Teachers
• Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning
• Automatic Curriculum Learning for Driving Scenarios: Towards Robust and Efficient Reinforcement Learning
• Backward Approximate Dynamic Programming with Hidden Semi-Markov Stochastic Models in Energy Storage Optimization
• Constant-Memory Strategies in Stochastic Games: Best Responses and Equilibria
• Factorization Regret mediates compositional generalization in latent space
• Provable Distributional Value Iteration under Partial Observability
• LLM-Guided Probabilistic Program Induction for POMDP Model Estimation
• The Advantage of Cross Entropy over Entropy in Iterative Information Gathering
• Working Memory Graphs
• Structure Learning in Motor Control:A Deep Reinforcement Learning Model
• KnowRob: A knowledge processing infrastructure for cognition-enabled robots
• Representations for robot knowledge in the KnowRob framework
• Can LLM Agents Be CFOs? Benchmarking Long-Horizon Resource Allocation in an Uncertain Enterprise Environment
• Bayesian Policy Search for Stochastic Domains
• Optimal Radio Frequency Energy Harvesting with Limited Energy Arrival Knowledge
• Adversarial observations in probabilistic State-Space Models for robust Reinforcement Learning
• Bayesian updates from coalgebraic determinisation
• Model Validation of Agentic AI Systems: A POMDP-Based Framework for Belief-State, Forecast, and Policy Validation
• MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents
• Belief at Risk: Quantifying Agentic AI Model Risk with LLM-Inferred Bayesian State Filters
• Risk-Aware Planning for Transit Desert Remediation Under Demand Uncertainty
• Hyperbolic Discounting and Learning over Multiple Horizons
• Understanding Domain Randomization for Sim-to-real Transfer
• Representations and solutions for game-theoretic problems
• Minimax-Optimal Policy Regret in Partially Observable Markov Games
• Cognitive maps are generative programs
• Adaptive AI Delegation under Uncertainty: A Bayesian Governance Policy for Sequential Decision Authority
• Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
• When Outcome Looks Right But Discipline Fails: Trace-Based Evaluation Under Hidden Competitor State
• 3D-Belief: Embodied Belief Inference via Generative 3D World Modeling
• The Auton Agentic AI Framework
• Human-level control through deep reinforcement learning
• An Imperfect Verifier is Good Enough: Learning with Noisy Rewards
• Coupled Control, Structured Memory, and Verifiable Action in Agentic AI (SCRAT -- Stochastic Control with Retrieval and Auditable Trajectories): A Comparative Perspective from Squirrel Locomotion and Scatter-Hoarding
• Generalized Inverse Planning: Learning Lifted non-Markovian Utility for Generalizable Task Representation
• LADDER: A Human-Level Bidding Agent for Large-Scale Real-Time Online Auctions
• On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning
• POMDPs for Autonomous Science Exploration
• Learning and Reasoning for Robot Dialog and Navigation Tasks
• Learning Attentive Neural Processes for Planning with Pushing Actions
• Robust Control under Stationary Ambiguity
• Belief Space Planning for Mobile Robots with Range Sensors using iLQG
• Optimal adaptive inspection and maintenance planning for deteriorating structural systems
• Learning enables adaptation in cooperation for multi-player stochastic games
• Finding Approximate POMDP solutions Through Belief Compression
• DESPOT: Online POMDP Planning with Regularization
• Safe and Effective Picking Paths in Clutter given Discrete Distributions of Object Poses
• A model of risk and mental state shifts during social interaction
• Multimodal Perception for Goal-oriented Navigation: A Survey
• Searching for a source without gradients: how good is infotaxis and how to beat it
• Optimal Decision-Making in Mixed-Agent Partially Observable Stochastic Environments via Reinforcement Learning
• AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability
• A Framework for Objective-Driven Dynamical Stochastic Fields
• Valuating Surface Surveillance Technology for Collaborative Multiple-Spot Control of Airport Departure Operations
• MPTP: Motion-planning-aware task planning for navigation in belief space
• Hidden Markov Models and Their Application for Predicting Failure Events
• Induction and Exploitation of Subgoal Automata for Reinforcement Learning
• Constrained Active Classification Using Partially Observable Markov Decision Processes
• AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
• Quantum-Structured World Models (QSWMs) for Predictive Latent Dynamics
• Timeline of artificial intelligence [wikipedia]
• The COACH prompting system to assist older adults with dementia through handwashing: an efficacy study. [europepmc]
• Reinforcement learning: Computational theory and biological mechanisms. [europepmc]
• Decision making under uncertainty: a neural model based on partially observable markov decision processes. [europepmc]
• The development of an adaptive upper-limb stroke rehabilitation robotic system. [europepmc]
• The nature of belief-directed exploratory choice in human decision-making. [europepmc]
• A computational framework for the study of confidence in humans and animals. [europepmc]
• The algorithmic anatomy of model-based evaluation. [europepmc]
• Monte Carlo Planning Method Estimates Planning Horizons during Interactive Social Exchange. [europepmc]
• Prospective Optimization with Limited Resources. [europepmc]
• Exploratory decision-making as a function of lifelong experience, not cognitive decline. [europepmc]
• A Probability Distribution over Latent Causes, in the Orbitofrontal Cortex. [europepmc]
• Reward-based training of recurrent neural networks for cognitive and value-based tasks. [europepmc]
• Predicting explorative motor learning using decision-making and motor noise. [europepmc]
• Heuristic and optimal policy computations in the human brain during sequential decision-making. [europepmc]
• A model of risk and mental state shifts during social interaction. [europepmc]
• Rational metareasoning and the plasticity of cognitive control. [europepmc]
• Multi-step planning of eye movements in visual search. [europepmc]
• Bayesian inference with incomplete knowledge explains perceptual confidence and its deviations from accuracy. [europepmc]
• Decision prioritization and causal reasoning in decision hierarchies. [europepmc]
• Optimism and pessimism in optimised replay. [europepmc]
• Epistemic Communities under Active Inference. [europepmc]
• Alternation emerges as a multi-modal strategy for turbulent odor navigation. [europepmc]
• Putting perception into action with inverse optimal control for continuous psychophysics. [europepmc]
• Reward Maximization Through Discrete Active Inference. [europepmc]
• Emergence of belief-like representations through reinforcement learning. [europepmc]