{"total":90,"rows":[{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237,"area":"wm"},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2307.04349","title":"RLTF: Reinforcement Learning from Unit Test Feedback","created":"2023-07-10","cited_by_count":114,"area":null},{"id":"2205.13320","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","created":"2022-05-26","cited_by_count":81,"area":null},{"id":"2205.13703","title":"Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters","created":"2022-05-27","cited_by_count":76,"area":"offlinerl"},{"id":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73,"area":"offlinerl"},{"id":"2110.14020","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","created":"2021-10-26","cited_by_count":50,"area":"offlinerl"},{"id":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"id":"2403.00564","title":"EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data","created":"2024-03-01","cited_by_count":40,"area":"wm"},{"id":"2210.00849","title":"Scaling Laws for a Multi-Agent Reinforcement Learning Model","created":"2022-09-29","cited_by_count":38,"area":"agents"},{"id":"2106.10316","title":"Proper Value Equivalence","created":"2021-06-18","cited_by_count":33,"area":null},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31,"area":"wm"},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2206.05314","title":"Large-Scale Retrieval for Reinforcement Learning","created":"2022-06-10","cited_by_count":24,"area":"offlinerl"},{"id":"2210.09598","title":"Planning for Sample Efficient Imitation Learning","created":"2022-10-18","cited_by_count":20,"area":"offlinerl"},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2310.20025","title":"GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models","created":"2023-10-30","cited_by_count":20,"area":"offlinerl"},{"id":"2109.15316","title":"Scalable Online Planning via Reinforcement Learning Fine-Tuning","created":"2021-09-30","cited_by_count":18,"area":null},{"id":"2411.01493","title":"Sample-Efficient Alignment for LLMs","created":"2024-11-03","cited_by_count":16,"area":"alignment"},{"id":"2505.11827","title":"Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning","created":"2025-05-17","cited_by_count":16,"area":"lr"},{"id":"2210.10763","title":"On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning","created":"2022-10-19","cited_by_count":15,"area":null},{"id":"2405.13863","title":"Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning","created":"2024-05-22","cited_by_count":15,"area":"deeprl"},{"id":"2301.13734","title":"Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design","created":"2023-01-31","cited_by_count":14,"area":null},{"id":"2410.00564","title":"Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining","created":"2024-10-01","cited_by_count":14,"area":"wm"},{"id":"2502.05454","title":"Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following","created":"2025-02-08","cited_by_count":14,"area":null},{"id":"2502.19009","title":"Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning","created":"2025-02-26","cited_by_count":13,"area":"deeprl"},{"id":"2406.10667","title":"UniZero: Generalized and Efficient Planning with Scalable Latent World Models","created":"2024-06-15","cited_by_count":12,"area":"wm"},{"id":"2203.07413","title":"Switch Trajectory Transformer with Distributional Value Approximation for Multi-Task Reinforcement Learning","created":"2022-03-14","cited_by_count":11,"area":null},{"id":"2410.11234","title":"Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning","created":"2024-10-15","cited_by_count":11,"area":"offlinerl"},{"id":"2107.01715","title":"Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction","created":"2021-07-04","cited_by_count":10,"area":null},{"id":"2411.08794","title":"LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Needed","created":"2024-11-13","cited_by_count":10,"area":"wm"},{"id":"2308.03526","title":"AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning","created":"2023-08-07","cited_by_count":9,"area":"offlinerl"},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2210.05980","title":"Efficient Offline Policy Optimization with a Learned Model","created":"2022-10-12","cited_by_count":8,"area":"offlinerl"},{"id":"2303.16189","title":"Planning with Sequence Models through Iterative Energy Minimization","created":"2023-03-28","cited_by_count":8,"area":null},{"id":"2110.12840","title":"Self-Consistent Models and Values","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2210.13455","title":"Epistemic Monte Carlo Tree Search","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2406.01423","title":"Value Improved Actor Critic Algorithms","created":"2024-06-03","cited_by_count":7,"area":"deeprl"},{"id":"2411.03820","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","created":"2024-11-06","cited_by_count":7,"area":"deeprl"},{"id":"2511.00423","title":"Bootstrap Off-policy with World Model","created":"2025-11-01","cited_by_count":7,"area":"wm"},{"id":"2306.00972","title":"Improving and Benchmarking Offline Reinforcement Learning Algorithms","created":"2023-06-01","cited_by_count":6,"area":"offlinerl"},{"id":"2307.03486","title":"Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning","created":"2023-07-07","cited_by_count":6,"area":null},{"id":"2309.12671","title":"How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization","created":"2023-09-22","cited_by_count":6,"area":null},{"id":"2406.00614","title":"Efficient Monte Carlo Tree Search via On-the-Fly State-Conditioned Action Abstraction","created":"2024-06-02","cited_by_count":6,"area":null},{"id":"2601.21306","title":"The Surprising Difficulty of Search in Model-Based Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"deeprl"},{"id":"2209.13126","title":"Design of experiments for the calibration of history-dependent models via deep reinforcement learning and an enhanced Kalman filter","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2302.00141","title":"Revisiting Bellman Errors for Offline Model Selection","created":"2023-01-31","cited_by_count":5,"area":"offlinerl"},{"id":"2302.04009","title":"Investigating the role of model-based learning in exploration and transfer","created":"2023-02-08","cited_by_count":5,"area":null},{"id":"2303.11369","title":"Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale","created":"2023-03-20","cited_by_count":5,"area":"offlinerl"},{"id":"2508.06659","title":"In-Context Reinforcement Learning via Communicative World Models","created":"2025-08-08","cited_by_count":5,"area":"wm"},{"id":"2106.08199","title":"On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning","created":"2021-06-15","cited_by_count":4,"area":"offlinerl"},{"id":"2307.06328","title":"Budgeting Counterfactual for Offline RL","created":"2023-07-12","cited_by_count":4,"area":"offlinerl"},{"id":"2312.12558","title":"Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge","created":"2023-12-19","cited_by_count":4,"area":null},{"id":"2502.21186","title":"Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction","created":"2025-02-28","cited_by_count":4,"area":"offlinerl"},{"id":"2112.01765","title":"Learning Emergent Random Access Protocol for LEO Satellite Networks","created":"2021-12-03","cited_by_count":3,"area":null},{"id":"2211.01743","title":"Beyond the Best: Estimating Distribution Functionals in Infinite-Armed Bandits","created":"2022-11-01","cited_by_count":3,"area":null},{"id":"2305.07440","title":"Optimizing Memory Mapping Using Deep Reinforcement Learning","created":"2023-05-11","cited_by_count":3,"area":null},{"id":"2310.06513","title":"Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction","created":"2023-10-10","cited_by_count":3,"area":null},{"id":"2310.11531","title":"Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2312.04216","title":"CODEX: A Cluster-Based Method for Explainable Reinforcement Learning","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2509.07945","title":"One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning","created":"2025-09-09","cited_by_count":3,"area":"wm"},{"id":"2511.14220","title":"Twice Sequential Monte Carlo for Tree Search","created":"2025-11-18","cited_by_count":3,"area":"deeprl"},{"id":"2202.04943","title":"Interpretable pipelines with evolutionarily optimized modules for RL tasks with visual inputs","created":"2022-02-10","cited_by_count":2,"area":null},{"id":"2209.06579","title":"C^2:Co-design of Robots via Concurrent Networks Coupling Online and Offline Reinforcement Learning","created":"2022-09-14","cited_by_count":2,"area":"offlinerl"},{"id":"2303.07046","title":"Deploying Offline Reinforcement Learning with Human Feedback","created":"2023-03-13","cited_by_count":2,"area":"alignment"},{"id":"2309.12560","title":"Machine Learning Meets Advanced Robotic Manipulation","created":"2023-09-22","cited_by_count":2,"area":null},{"id":"2404.16364","title":"ReZero: Boosting MCTS-based Algorithms by Backward-view and Entire-buffer Reanalyze","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2509.10504","title":"Retrosynthesis Planning via Worst-path Policy Optimisation in Tree-structured MDPs","created":"2025-09-01","cited_by_count":2,"area":null},{"id":"2510.04280","title":"A KL-regularization Framework for Learning to Plan with Adaptive Priors","created":"2025-10-05","cited_by_count":2,"area":"deeprl"},{"id":"2511.10843","title":"Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning","created":"2025-11-13","cited_by_count":2,"area":"deeprl"},{"id":"2608.17163","title":"Q-Learning With World Models","created":"2026-08-17","cited_by_count":2,"area":"wm"},{"id":"2106.14080","title":"Model-Advantage and Value-Aware Models for Model-Based Reinforcement Learning: Bridging the Gap in Theory and Practice","created":"2021-06-26","cited_by_count":1,"area":null},{"id":"2108.06148","title":"Q-Mixing Network for Multi-Agent Pathfinding in Partially Observable Grid Environments","created":"2021-08-13","cited_by_count":1,"area":null},{"id":"2304.12151","title":"Policy Resilience to Environment Poisoning Attacks on Reinforcement Learning","created":"2023-04-24","cited_by_count":1,"area":null},{"id":"2310.01569","title":"Iterative Option Discovery for Planning, by Planning","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2404.10393","title":"Offline Trajectory Optimization for Offline Reinforcement Learning","created":"2024-04-16","cited_by_count":1,"area":"offlinerl"},{"id":"2506.05748","title":"Efficient Online RFT with Plug-and-Play LLM Judges: Unlocking State-of-the-Art Performance","created":"2025-06-06","cited_by_count":1,"area":"alignment"},{"id":"2509.05735","title":"Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies","created":"2025-09-06","cited_by_count":1,"area":"wm"},{"id":"2512.04341","title":"Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism","created":"2025-12-04","cited_by_count":1,"area":"offlinerl"},{"id":"2602.10894","title":"Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games","created":"2026-02-11","cited_by_count":1,"area":"deeprl"},{"id":"2605.11711","title":"Debiased Model-based Representations for Sample-efficient Continuous Control","created":"2026-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2205.10739","title":"Offline Policy Comparison with Confidence: Benchmarks and Baselines","created":"2022-05-22","cited_by_count":0,"area":null},{"id":"2306.03408","title":"Agents Explore the Environment Beyond Good Actions to Improve Their Model for Better Decisions","created":"2023-06-06","cited_by_count":0,"area":null},{"id":"2308.08693","title":"AI planning in the imagination: High-level planning on learned abstract search spaces","created":"2023-08-16","cited_by_count":0,"area":null},{"id":"2405.12001","title":"Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning","created":"2024-05-20","cited_by_count":0,"area":null},{"id":"2603.27751","title":"SkyNet: Belief-Aware Planning for Partially-Observable Stochastic Games","created":"2026-03-29","cited_by_count":0,"area":"deeprl"},{"id":"2607.26946","title":"Belief-Guided Decision Making with Uncertainty Gating in the Game of Go","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.21735","title":"GEM-MPC: Balancing Exploration and Exploitation through Expert-Guided Planning","created":"2026-09-18","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}