{"total":327,"rows":[{"id":"2402.12275","title":"WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment","created":"2024-02-19","cited_by_count":107,"area":"wm"},{"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":"2402.16801","title":"Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning","created":"2024-02-26","cited_by_count":88,"area":"deeprl"},{"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":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2311.11385","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","created":"2023-11-19","cited_by_count":49,"area":null},{"id":"2403.12014","title":"EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents","created":"2024-03-18","cited_by_count":46,"area":"agents"},{"id":"2407.17032","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","created":"2024-07-24","cited_by_count":46,"area":"deeprl"},{"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":"2402.04764","title":"Code as Reward: Empowering Reinforcement Learning with VLMs","created":"2024-02-07","cited_by_count":39,"area":"mllm"},{"id":"2408.15099","title":"No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery","created":"2024-08-27","cited_by_count":31,"area":"deeprl"},{"id":"2311.13373","title":"Large Language Model as a Policy Teacher for Training Reinforcement Learning Agents","created":"2023-11-22","cited_by_count":30,"area":"agents"},{"id":"2401.11237","title":"Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View","created":"2024-01-20","cited_by_count":27,"area":"deeprl"},{"id":"2503.13415","title":"A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives","created":"2025-03-17","cited_by_count":27,"area":"agents"},{"id":"2510.23691","title":"Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents","created":"2025-10-27","cited_by_count":24,"area":"agents"},{"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":"2502.12272","title":"Learning to Reason at the Frontier of Learnability","created":"2025-02-17","cited_by_count":23,"area":"lr"},{"id":"2505.05522","title":"Continuous Thought Machines","created":"2025-05-08","cited_by_count":22,"area":null},{"id":"2402.02423","title":"Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback","created":"2024-02-04","cited_by_count":21,"area":"alignment"},{"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":"2411.03865","title":"AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making","created":"2024-11-06","cited_by_count":20,"area":"agents"},{"id":"2511.11478","title":"Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective","created":"2025-11-14","cited_by_count":20,"area":"vla"},{"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":"2505.22246","title":"StateSpaceDiffuser: Bringing Long Context to Diffusion World Models","created":"2025-05-28","cited_by_count":19,"area":"wm"},{"id":"2402.05828","title":"Discovering Temporally-Aware Reinforcement Learning Algorithms","created":"2024-02-08","cited_by_count":18,"area":"deeprl"},{"id":"2407.19396","title":"NAVIX: Scaling MiniGrid Environments with JAX","created":"2024-07-28","cited_by_count":18,"area":"deeprl"},{"id":"2506.21872","title":"A Survey of Continual Reinforcement Learning","created":"2025-06-27","cited_by_count":18,"area":"deeprl"},{"id":"2402.03046","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","created":"2024-02-05","cited_by_count":17,"area":"deeprl"},{"id":"2501.15418","title":"Episodic Novelty Through Temporal Distance","created":"2025-01-26","cited_by_count":16,"area":"deeprl"},{"id":"2411.11188","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","created":"2024-11-17","cited_by_count":15,"area":"deeprl"},{"id":"2406.08973","title":"XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning","created":"2024-06-13","cited_by_count":14,"area":"deeprl"},{"id":"2407.07082","title":"Can Learned Optimization Make Reinforcement Learning Less Difficult?","created":"2024-07-09","cited_by_count":14,"area":"deeprl"},{"id":"2503.20124","title":"Synthesizing world models for bilevel planning","created":"2025-03-26","cited_by_count":14,"area":"wm"},{"id":"2505.02216","title":"LLM-Guided Probabilistic Program Induction for POMDP Model Estimation","created":"2025-05-04","cited_by_count":12,"area":null},{"id":"2312.01203","title":"Harnessing Discrete Representations For Continual Reinforcement Learning","created":"2023-12-02","cited_by_count":11,"area":"wm"},{"id":"2403.13091","title":"JaxUED: A simple and useable UED library in Jax","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2406.00120","title":"Reward Machines for Deep RL in Noisy and Uncertain Environments","created":"2024-05-31","cited_by_count":11,"area":"deeprl"},{"id":"2406.17949","title":"The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design","created":"2024-06-25","cited_by_count":11,"area":"deeprl"},{"id":"2505.19281","title":"A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning","created":"2025-05-25","cited_by_count":11,"area":"deeprl"},{"id":"2403.13765","title":"Towards Principled Representation Learning from Videos for Reinforcement Learning","created":"2024-03-20","cited_by_count":10,"area":"deeprl"},{"id":"2405.19548","title":"RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning","created":"2024-05-29","cited_by_count":10,"area":"deeprl"},{"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":"2410.19715","title":"Adversarial Environment Design via Regret-Guided Diffusion Models","created":"2024-10-25","cited_by_count":10,"area":"diffusion"},{"id":"2410.22133","title":"Learning Successor Features the Simple Way","created":"2024-10-29","cited_by_count":10,"area":"deeprl"},{"id":"2502.16690","title":"From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task","created":"2025-02-23","cited_by_count":10,"area":"agents"},{"id":"2504.14898","title":"Expected Free Energy-based Planning as Variational Inference","created":"2025-04-21","cited_by_count":10,"area":null},{"id":"2505.20659","title":"An Optimisation Framework for Unsupervised Environment Design","created":"2025-05-27","cited_by_count":10,"area":"deeprl"},{"id":"2510.12088","title":"One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration","created":"2025-10-14","cited_by_count":10,"area":"wm"},{"id":"2311.03357","title":"Exploitation-Guided Exploration for Semantic Embodied Navigation","created":"2023-11-06","cited_by_count":9,"area":null},{"id":"2409.15703","title":"Agent-state based policies in POMDPs: Beyond belief-state MDPs","created":"2024-09-24","cited_by_count":9,"area":"deeprl"},{"id":"2410.05656","title":"On the Modeling Capabilities of Large Language Models for Sequential Decision Making","created":"2024-10-08","cited_by_count":9,"area":"alignment"},{"id":"2503.01584","title":"SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models","created":"2025-03-03","cited_by_count":9,"area":"wm"},{"id":"2503.15200","title":"Partially Observable Reinforcement Learning with Memory Traces","created":"2025-03-19","cited_by_count":9,"area":"deeprl"},{"id":"2603.30043","title":"Video Models Reason Early: Exploiting Plan Commitment for Maze Solving","created":"2026-03-31","cited_by_count":9,"area":"lr"},{"id":"2406.15599","title":"Pareto-Optimal Learning from Preferences with Hidden Context","created":"2024-06-21","cited_by_count":8,"area":"alignment"},{"id":"2411.00773","title":"LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation","created":"2024-11-01","cited_by_count":8,"area":"lr"},{"id":"2501.11533","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","created":"2025-01-20","cited_by_count":8,"area":"deeprl"},{"id":"2503.00799","title":"On Generalization Across Environments In Multi-Objective Reinforcement Learning","created":"2025-03-02","cited_by_count":8,"area":"deeprl"},{"id":"2601.01075","title":"Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments","created":"2026-01-03","cited_by_count":8,"area":"wm"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2402.05284","title":"Analyzing Adversarial Inputs in Deep Reinforcement Learning","created":"2024-02-07","cited_by_count":7,"area":"deeprl"},{"id":"2405.02481","title":"Proximal Curriculum with Task Correlations for Deep Reinforcement Learning","created":"2024-05-03","cited_by_count":7,"area":"deeprl"},{"id":"2405.20018","title":"Safe Multi-agent Reinforcement Learning with Natural Language Constraints","created":"2024-05-30","cited_by_count":7,"area":"agents"},{"id":"2406.02035","title":"A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning","created":"2024-06-04","cited_by_count":7,"area":"deeprl"},{"id":"2407.01892","title":"GRASP: A Grid-Based Benchmark for Evaluating Commonsense Spatial Reasoning","created":"2024-07-02","cited_by_count":7,"area":"lr"},{"id":"2409.15922","title":"The Dark Side of Rich Rewards: Understanding and Mitigating Noise in VLM Rewards","created":"2024-09-24","cited_by_count":7,"area":"mllm"},{"id":"2410.15221","title":"IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning","created":"2024-10-19","cited_by_count":7,"area":"driving"},{"id":"2411.10175","title":"The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning","created":"2024-11-15","cited_by_count":7,"area":"deeprl"},{"id":"2503.04256","title":"Knowledge Retention for Continual Model-Based Reinforcement Learning","created":"2025-03-06","cited_by_count":7,"area":"wm"},{"id":"2503.23478","title":"Handling Delay in Real-Time Reinforcement Learning","created":"2025-03-30","cited_by_count":7,"area":"deeprl"},{"id":"2505.03209","title":"DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning","created":"2025-05-06","cited_by_count":7,"area":"offlinerl"},{"id":"2508.00046","title":"Benchmarking Partial Observability in Reinforcement Learning with a Suite of Memory-Improvable Domains","created":"2025-07-31","cited_by_count":7,"area":"deeprl"},{"id":"2604.07036","title":"ReDAct: Uncertainty-Aware Deferral for LLM Agents","created":"2026-04-08","cited_by_count":7,"area":"agents"},{"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":"2312.03446","title":"Visual Hindsight Self-Imitation Learning for Interactive Navigation","created":"2023-12-05","cited_by_count":6,"area":"offlinerl"},{"id":"2401.15098","title":"Multi-granularity Knowledge Transfer for Continual Reinforcement Learning","created":"2024-01-25","cited_by_count":6,"area":"deeprl"},{"id":"2403.08955","title":"Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis","created":"2024-03-13","cited_by_count":6,"area":"deeprl"},{"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":"2503.08241","title":"HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents","created":"2025-03-11","cited_by_count":6,"area":"deeprl"},{"id":"2603.07432","title":"Generalization in Online Reinforcement Learning for Mobile Agents","created":"2026-03-08","cited_by_count":6,"area":"lr"},{"id":"2608.04653","title":"Overcoming Statistical Bias in Action-Controllable World Models","created":"2026-08-05","cited_by_count":6,"area":"wm"},{"id":"2407.15786","title":"LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learning","created":"2024-07-22","cited_by_count":5,"area":"lr"},{"id":"2407.16220","title":"ODGR: Online Dynamic Goal Recognition","created":"2024-07-23","cited_by_count":5,"area":"deeprl"},{"id":"2408.08761","title":"Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization","created":"2024-08-16","cited_by_count":5,"area":"deeprl"},{"id":"2412.06531","title":"Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation","created":"2024-12-09","cited_by_count":5,"area":"deeprl"},{"id":"2502.03450","title":"Schema-Guided Scene-Graph Reasoning based on Multi-Agent Large Language Model System","created":"2025-02-05","cited_by_count":5,"area":"lr"},{"id":"2503.07002","title":"Taking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue Learning","created":"2025-03-10","cited_by_count":5,"area":"mllm"},{"id":"2505.09003","title":"Continual Reinforcement Learning via Autoencoder-Driven Task and New Environment Recognition","created":"2025-05-13","cited_by_count":5,"area":"deeprl"},{"id":"2507.08210","title":"From Curiosity to Competence: How World Models Interact with the Dynamics of Exploration","created":"2025-07-10","cited_by_count":5,"area":"wm"},{"id":"2508.02197","title":"A Message Passing Realization of Expected Free Energy Minimization","created":"2025-08-04","cited_by_count":5,"area":null},{"id":"2508.06659","title":"In-Context Reinforcement Learning via Communicative World Models","created":"2025-08-08","cited_by_count":5,"area":"wm"},{"id":"2510.14176","title":"ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning","created":"2025-10-16","cited_by_count":5,"area":"deeprl"},{"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":"2407.12437","title":"Variable-Agnostic Causal Exploration for Reinforcement Learning","created":"2024-07-17","cited_by_count":4,"area":"deeprl"}],"next_cursor":"100"}