{"total":90,"rows":[{"id":"2406.06769","title":"DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents","created":"2024-06-10","cited_by_count":100,"area":null},{"id":"2312.09238","title":"Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft","created":"2023-12-14","cited_by_count":61,"area":null},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55,"area":null},{"id":"2311.11385","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","created":"2023-11-19","cited_by_count":49,"area":null},{"id":"2410.23208","title":"Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks","created":"2024-10-30","cited_by_count":45,"area":null},{"id":"2310.01824","title":"Mini-BEHAVIOR: A Procedurally Generated Benchmark for Long-horizon Decision-Making in Embodied AI","created":"2023-10-03","cited_by_count":23,"area":null},{"id":"2505.05522","title":"Continuous Thought Machines","created":"2025-05-08","cited_by_count":22,"area":null},{"id":"2402.09844","title":"Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent","created":"2024-02-15","cited_by_count":21,"area":null},{"id":"2311.04193","title":"Selective Visual Representations Improve Convergence and Generalization for Embodied AI","created":"2023-11-07","cited_by_count":19,"area":null},{"id":"2505.02216","title":"LLM-Guided Probabilistic Program Induction for POMDP Model Estimation","created":"2025-05-04","cited_by_count":12,"area":null},{"id":"2403.13091","title":"JaxUED: A simple and useable UED library in Jax","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2407.13729","title":"Baba Is AI: Break the Rules to Beat the Benchmark","created":"2024-07-18","cited_by_count":10,"area":null},{"id":"2504.14898","title":"Expected Free Energy-based Planning as Variational Inference","created":"2025-04-21","cited_by_count":10,"area":null},{"id":"2311.03357","title":"Exploitation-Guided Exploration for Semantic Embodied Navigation","created":"2023-11-06","cited_by_count":9,"area":null},{"id":"2307.03486","title":"Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning","created":"2023-07-07","cited_by_count":6,"area":null},{"id":"2309.13043","title":"E(2)-Equivariant Graph Planning for Navigation","created":"2023-09-22","cited_by_count":6,"area":null},{"id":"2411.07954","title":"Learning Memory Mechanisms for Decision Making through Demonstrations","created":"2024-11-12","cited_by_count":6,"area":null},{"id":"2412.07207","title":"MAPLE: A Framework for Active Preference Learning Guided by Large Language Models","created":"2024-12-10","cited_by_count":6,"area":null},{"id":"2508.02197","title":"A Message Passing Realization of Expected Free Energy Minimization","created":"2025-08-04","cited_by_count":5,"area":null},{"id":"2402.06590","title":"Predictive representations: building blocks of intelligence","created":"2024-02-09","cited_by_count":4,"area":null},{"id":"2406.11334","title":"Program Synthesis Benchmark for Visual Programming in XLogoOnline Environment","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2407.03964","title":"Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2407.03969","title":"Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2410.05869","title":"Believing is Seeing: Unobserved Object Detection using Generative Models","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2410.09187","title":"Automated Rewards via LLM-Generated Progress Functions","created":"2024-10-11","cited_by_count":4,"area":null},{"id":"2502.05726","title":"Improving Environment Novelty Quantification for Effective Unsupervised Environment Design","created":"2025-02-08","cited_by_count":4,"area":null},{"id":"2508.18420","title":"LLM-Driven Intrinsic Motivation for Sparse Reward Reinforcement Learning","created":"2025-08-25","cited_by_count":4,"area":null},{"id":"2509.17393","title":"Program Synthesis via Test-Time Transduction","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2605.06734","title":"Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2312.11414","title":"The Animal-AI Environment: A Virtual Laboratory For Comparative Cognition and Artificial Intelligence Research","created":"2023-12-18","cited_by_count":2,"area":null},{"id":"2401.00031","title":"Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges","created":"2023-12-29","cited_by_count":2,"area":null},{"id":"2403.17497","title":"Sharing the Cost of Success: A Game for Evaluating and Learning Collaborative Multi-Agent Instruction Giving and Following Policies","created":"2024-03-26","cited_by_count":2,"area":null},{"id":"2407.04158","title":"ELCC: the Emergent Language Corpus Collection","created":"2024-07-04","cited_by_count":2,"area":null},{"id":"2502.13935","title":"Foundations of a Developmental Design Paradigm for Integrated Continual Learning, Deliberative Behavior, and Comprehensibility","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2502.16736","title":"Adaptive Conformal Guidance for Learning under Uncertainty","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2504.10253","title":"TinyverseGP: Towards a Modular Cross-domain Benchmarking Framework for Genetic Programming","created":"2025-04-14","cited_by_count":2,"area":null},{"id":"2505.00490","title":"Optimal Interactive Learning on the Job via Facility Location Planning","created":"2025-05-01","cited_by_count":2,"area":null},{"id":"2601.20116","title":"In-Context Reinforcement Learning From Suboptimal Historical Data","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2604.01577","title":"Exploration of Fast-Slow Latent Recurrence for Train-Short, Test-Long Generalization","created":"2026-04-02","cited_by_count":2,"area":null},{"id":"2605.28918","title":"When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2607.02440","title":"EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2309.17275","title":"Utility-based Adaptive Teaching Strategies using Bayesian Theory of Mind","created":"2023-09-29","cited_by_count":1,"area":null},{"id":"2311.07312","title":"C-Procgen: Empowering Procgen with Controllable Contexts","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2311.15960","title":"Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2311.18703","title":"Predictable Reinforcement Learning Dynamics through Entropy Rate Minimization","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2402.15393","title":"NeuralSolver: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks","created":"2024-02-23","cited_by_count":1,"area":null},{"id":"2405.16588","title":"Attaining Human`s Desirable Outcomes in Human-AI Interaction via Structural Causal Games","created":"2024-05-26","cited_by_count":1,"area":null},{"id":"2407.09809","title":"Preserving the Privacy of Reward Functions in MDPs through Deception","created":"2024-07-13","cited_by_count":1,"area":null},{"id":"2410.03565","title":"Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2410.07096","title":"Rejecting Hallucinated State Targets during Planning","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2501.08925","title":"Disentangling Exploration of Large Language Models by Optimal Exploitation","created":"2025-01-15","cited_by_count":1,"area":null},{"id":"2504.06468","title":"Agent-Arena: A General Framework for Evaluating Control Algorithms","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2505.13196","title":"A Physics-Inspired Optimizer: Velocity Regularized Adam","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.20579","title":"The challenge of hidden gifts in multi-agent reinforcement learning","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2506.05702","title":"Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Spaces","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2507.14906","title":"Feedback-Induced Performance Decline in LLM-Based Decision-Making","created":"2025-07-20","cited_by_count":1,"area":null},{"id":"2509.09790","title":"How well can LLMs provide planning feedback in grounded environments?","created":"2025-09-11","cited_by_count":1,"area":null},{"id":"2510.01531","title":"Information Seeking for Robust Decision Making under Partial Observability","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2511.03256","title":"Decoupled Entropy Minimization","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2603.28386","title":"COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments via Two-Player Zero-Sum Game","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2604.17019","title":"Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2607.02087","title":"SUNTA: Hierarchical Video Prediction with Surprise-based Chunking","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.16421","title":"When to Plan: Learning to Select Between Reactive Control and Deliberative Planning","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2608.11511","title":"Let it Cook: Learning to Wait in Sequential Decision Making","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2609.36473","title":"Going Beyond State-Reaching: Learning Abstractions for Intrinsically Motivated Option Discovery","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2407.08065","title":"Towards Interpretable Foundation Models of Robot Behavior: A Task Specific Policy Generation Approach","created":"2024-07-10","cited_by_count":0,"area":null},{"id":"2410.06372","title":"Cooperative and Asynchronous Transformer-based Mission Planning for Heterogeneous Teams of Mobile Robots","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2501.12539","title":"Compositional Instruction Following with Language Models and Reinforcement Learning","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2502.09583","title":"YRC-Bench: A Benchmark for Learning to Coordinate with Experts","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2505.03941","title":"GRAML: Goal Recognition As Metric Learning","created":"2025-05-06","cited_by_count":0,"area":null},{"id":"2509.08329","title":"Accelerating Reinforcement Learning Algorithms Convergence using Pre-trained Large Language Models as Tutors With Advice Reusing","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2511.17165","title":"MIR: Efficient Exploration in Episodic Multi-Agent Reinforcement Learning via Mutual Intrinsic Reward","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2511.18955","title":"Active Inference is a Subtype of Variational Inference","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.06982","title":"LLM-Driven Composite Neural Architecture Search for Multi-Source RL State Encoding","created":"2025-12-07","cited_by_count":0,"area":null},{"id":"2602.01665","title":"TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.12753","title":"Hierarchical Successor Representation for Robust Transfer","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2604.08355","title":"ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.15044","title":"CoGrid & the Multi-User Gymnasium: A Framework for Multi-Agent Experimentation","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.27162","title":"A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.05795","title":"Reward Shaping and Action Masking for Compositional Tasks using Behavior Trees and LLMs","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.07174","title":"Repeated Deceptive Path Planning against Learnable Observer","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.08681","title":"Core-Halo Decomposition: Decentralizing Large-Scale Fixed-Point Problems","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.06123","title":"Adaptive state-action abstractions via rate-distortion","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.06673","title":"Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.20658","title":"Expected Free Energy-based Planning as Variational Inference","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.29541","title":"Learned Coordination Conventions in Cooperative MARL: Measuring the Translation Gap Between Theory-Informed Roles and Learned Routing","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.07753","title":"A Transdiagnostic Space of Disorder Like Phenotypes in Reinforcement Learning Agents","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.01130","title":"When Do Surrogate Updates Improve Decisions? A Local Theory of Trajectory-Wise Transfer","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2609.16056","title":"Managing Action Preconditions in Neuro-Symbolic RL: Three Placement Strategies for Embodied Agents","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2610.14953","title":"Counterfactual Rollouts for Offline Contrastive Goal-Conditioned Reinforcement Learning","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}