{"total":28,"rows":[{"id":"2302.05446","title":"Robust Scheduling with GFlowNets","created":"2023-01-17","cited_by_count":69,"area":null},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2109.11052","title":"On Bonus-Based Exploration Methods in the Arcade Learning Environment","created":"2021-09-22","cited_by_count":37,"area":null},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2105.05347","title":"Return-based Scaling: Yet Another Normalisation Trick for Deep RL","created":"2021-05-11","cited_by_count":23,"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":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2206.02126","title":"Learning Dynamics and Generalization in Reinforcement Learning","created":"2022-06-05","cited_by_count":14,"area":null},{"id":"2112.00597","title":"Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation","created":"2021-12-01","cited_by_count":13,"area":null},{"id":"2102.12924","title":"Visualizing MuZero Models","created":"2021-02-25","cited_by_count":9,"area":null},{"id":"2106.15419","title":"Convergent and Efficient Deep Q Network Algorithm","created":"2021-06-29","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":"2106.06170","title":"Taylor Expansion of Discount Factors","created":"2021-06-11","cited_by_count":4,"area":null},{"id":"2104.14138","title":"Adapting to Reward Progressivity via Spectral Reinforcement Learning","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2306.04403","title":"Policy-Based Self-Competition for Planning Problems","created":"2023-06-07","cited_by_count":3,"area":null},{"id":"2112.07424","title":"Conjugated Discrete Distributions for Distributional Reinforcement Learning","created":"2021-12-14","cited_by_count":2,"area":null},{"id":"2209.09329","title":"MAN: Multi-Action Networks Learning","created":"2022-09-19","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":"2201.08610","title":"Deep Q-learning: a robust control approach","created":"2022-01-21","cited_by_count":1,"area":null},{"id":"2210.00828","title":"Mastering Spatial Graph Prediction of Road Networks","created":"2022-10-03","cited_by_count":1,"area":null},{"id":"2207.12505","title":"On the benefits of non-linear weight updates","created":"2022-07-25","cited_by_count":0,"area":null},{"id":"2211.02466","title":"Network Aware Compute and Memory Allocation in Optically Composable Data Centres with Deep Reinforcement Learning and Graph Neural Networks","created":"2022-10-26","cited_by_count":0,"area":null},{"id":"2212.05377","title":"Generalization Through the Lens of Learning Dynamics","created":"2022-12-11","cited_by_count":0,"area":null},{"id":"2212.10705","title":"Control of Continuous Quantum Systems with Many Degrees of Freedom based on Convergent Reinforcement Learning","created":"2022-12-21","cited_by_count":0,"area":null},{"id":"2302.12403","title":"Plume: A Framework for High Performance Deep RL Network Controllers via Prioritized Trace Sampling","created":"2023-02-24","cited_by_count":0,"area":null},{"id":"2302.13483","title":"CrystalBox: Future-Based Explanations for Input-Driven Deep RL Systems","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2310.06415","title":"Deep reinforcement learning uncovers processes for separating azeotropic mixtures without prior knowledge","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2610.15046","title":"Belief Embedding Tree Search","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}