{"total":43,"rows":[{"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":"2106.10316","title":"Proper Value Equivalence","created":"2021-06-18","cited_by_count":33,"area":null},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"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":"2109.15316","title":"Scalable Online Planning via Reinforcement Learning Fine-Tuning","created":"2021-09-30","cited_by_count":18,"area":null},{"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":"2301.13734","title":"Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design","created":"2023-01-31","cited_by_count":14,"area":null},{"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":"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":"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":"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":"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":"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":"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":"2302.04009","title":"Investigating the role of model-based learning in exploration and transfer","created":"2023-02-08","cited_by_count":5,"area":null},{"id":"2312.12558","title":"Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge","created":"2023-12-19","cited_by_count":4,"area":null},{"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":"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":"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":"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":"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":"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}],"next_cursor":null}