{"total":52,"rows":[{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59,"area":null},{"id":"2107.03974","title":"Offline Meta-Reinforcement Learning with Online Self-Supervision","created":"2021-07-08","cited_by_count":53,"area":"offlinerl"},{"id":"2110.03909","title":"Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning","created":"2021-10-08","cited_by_count":49,"area":null},{"id":"2211.11260","title":"Discovering Evolution Strategies via Meta-Black-Box Optimization","created":"2022-11-21","cited_by_count":44,"area":null},{"id":"2104.06272","title":"Podracer architectures for scalable Reinforcement Learning","created":"2021-04-13","cited_by_count":38,"area":null},{"id":"2304.03995","title":"Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization","created":"2023-04-08","cited_by_count":33,"area":null},{"id":"2109.10781","title":"Introducing Symmetries to Black Box Meta Reinforcement Learning","created":"2021-09-22","cited_by_count":25,"area":null},{"id":"2206.03271","title":"On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning","created":"2022-06-07","cited_by_count":19,"area":null},{"id":"2211.15457","title":"Hypernetworks for Zero-shot Transfer in Reinforcement Learning","created":"2022-11-28","cited_by_count":19,"area":null},{"id":"2110.03375","title":"Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning","created":"2021-10-07","cited_by_count":18,"area":null},{"id":"2301.10339","title":"AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning","created":"2023-01-24","cited_by_count":17,"area":null},{"id":"2310.02782","title":"Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design","created":"2023-10-04","cited_by_count":16,"area":null},{"id":"2310.19007","title":"Behavior Alignment via Reward Function Optimization","created":"2023-10-29","cited_by_count":16,"area":null},{"id":"2403.06826","title":"In-context Exploration-Exploitation for Reinforcement Learning","created":"2024-03-11","cited_by_count":16,"area":"offlinerl"},{"id":"2101.07367","title":"Training Learned Optimizers with Randomly Initialized Learned Optimizers","created":"2021-01-14","cited_by_count":13,"area":null},{"id":"2112.09245","title":"Automated Deep Learning: Neural Architecture Search Is Not the End","created":"2021-12-16","cited_by_count":13,"area":null},{"id":"2210.06041","title":"Reinforcement Learning with Automated Auxiliary Loss Search","created":"2022-10-12","cited_by_count":13,"area":null},{"id":"2307.14993","title":"Thinker: Learning to Plan and Act","created":"2023-07-27","cited_by_count":13,"area":"wm"},{"id":"2112.09025","title":"Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs","created":"2021-12-16","cited_by_count":12,"area":null},{"id":"2112.15400","title":"A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning","created":"2021-12-31","cited_by_count":12,"area":null},{"id":"2302.01470","title":"Learning to Optimize for Reinforcement Learning","created":"2023-02-03","cited_by_count":12,"area":null},{"id":"2209.06159","title":"Meta-Gradients in Non-Stationary Environments","created":"2022-09-13","cited_by_count":11,"area":null},{"id":"2201.05000","title":"Automated Reinforcement Learning: An Overview","created":"2022-01-13","cited_by_count":9,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2401.02349","title":"A Survey Analyzing Generalization in Deep Reinforcement Learning","created":"2024-01-04","cited_by_count":8,"area":"deeprl"},{"id":"2401.17401","title":"Step-size Optimization for Continual Learning","created":"2024-01-30","cited_by_count":6,"area":null},{"id":"2506.15446","title":"Zero-Shot Reinforcement Learning Under Partial Observability","created":"2025-06-18","cited_by_count":6,"area":"deeprl"},{"id":"2106.13125","title":"Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation","created":"2021-06-24","cited_by_count":5,"area":null},{"id":"2111.00206","title":"One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learning","created":"2021-10-30","cited_by_count":5,"area":null},{"id":"2112.07328","title":"Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement Learning","created":"2021-12-14","cited_by_count":5,"area":null},{"id":"2209.11303","title":"An Investigation of the Bias-Variance Tradeoff in Meta-Gradients","created":"2022-09-22","cited_by_count":5,"area":null},{"id":"2102.04999","title":"Adaptive Pairwise Weights for Temporal Credit Assignment","created":"2021-02-09","cited_by_count":2,"area":null},{"id":"2106.02745","title":"Neural Auto-Curricula","created":"2021-06-04","cited_by_count":2,"area":null},{"id":"2210.14361","title":"Auxiliary task discovery through generate-and-test","created":"2022-10-25","cited_by_count":2,"area":null},{"id":"2301.03236","title":"Optimistic Meta-Gradients","created":"2023-01-09","cited_by_count":2,"area":null},{"id":"2502.02190","title":"Discovering Quality-Diversity Algorithms via Meta-Black-Box Optimization","created":"2025-02-04","cited_by_count":2,"area":null},{"id":"2204.04292","title":"Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability","created":"2022-04-08","cited_by_count":1,"area":null},{"id":"2407.21546","title":"Black Box Meta-Learning Intrinsic Rewards","created":"2024-07-31","cited_by_count":1,"area":"deeprl"},{"id":"2504.03793","title":"Outlook Towards Deployable Continual Learning for Particle Accelerators","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2505.07911","title":"Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review","created":"2025-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2512.13399","title":"Dual-Evolving Reinforcement Learning for Automated Reward Design","created":"2025-12-15","cited_by_count":1,"area":"deeprl"},{"id":"2204.02210","title":"Model Based Meta Learning of Critics for Policy Gradients","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2211.10550","title":"Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function","created":"2022-11-19","cited_by_count":0,"area":null},{"id":"2306.10587","title":"Acceleration in Policy Optimization","created":"2023-06-18","cited_by_count":0,"area":null},{"id":"2309.13181","title":"Diagnosing and exploiting the computational demands of videos games for deep reinforcement learning","created":"2023-09-22","cited_by_count":0,"area":null},{"id":"2410.12598","title":"Dynamic Learning Rate for Deep Reinforcement Learning: A Bandit Approach","created":"2024-10-16","cited_by_count":0,"area":"deeprl"},{"id":"2501.07346","title":"Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data","created":"2025-01-13","cited_by_count":0,"area":"offlinerl"},{"id":"2510.23448","title":"An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning","created":"2025-10-27","cited_by_count":0,"area":"deeprl"},{"id":"2512.15948","title":"Subjective functions","created":"2025-12-17","cited_by_count":0,"area":null}],"next_cursor":null}