{"total":28,"rows":[{"id":"2106.11144","title":"Scientific multi-agent reinforcement learning for wall-models of turbulent flows","created":"2021-06-21","cited_by_count":52,"area":null},{"id":"2111.02552","title":"Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies","created":"2021-11-03","cited_by_count":38,"area":null},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"area":null},{"id":"2102.10536","title":"Learning Efficient Navigation in Vortical Flow Fields","created":"2021-02-21","cited_by_count":26,"area":null},{"id":"2209.00532","title":"Actor Prioritized Experience Replay","created":"2022-09-01","cited_by_count":20,"area":null},{"id":"2302.10418","title":"MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization","created":"2023-02-21","cited_by_count":20,"area":null},{"id":"2101.02034","title":"Deep Reinforcement Learning with Quantum-inspired Experience Replay","created":"2021-01-06","cited_by_count":19,"area":null},{"id":"2207.12141","title":"Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy","created":"2022-07-25","cited_by_count":17,"area":null},{"id":"2306.15934","title":"Curious Replay for Model-based Adaptation","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2208.14307","title":"Beyond Supervised Continual Learning: a Review","created":"2022-08-30","cited_by_count":11,"area":null},{"id":"2106.05526","title":"Simplifying Deep Reinforcement Learning via Self-Supervision","created":"2021-06-10","cited_by_count":9,"area":null},{"id":"2109.11767","title":"Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience","created":"2021-09-24","cited_by_count":8,"area":null},{"id":"2202.11664","title":"Comparative analysis of machine learning methods for active flow control","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2305.02054","title":"Map-based Experience Replay: A Memory-Efficient Solution to Catastrophic Forgetting in Reinforcement Learning","created":"2023-05-03","cited_by_count":6,"area":null},{"id":"2105.00771","title":"Learning swimming escape patterns for larval fish under energy constraints","created":"2021-05-03","cited_by_count":3,"area":null},{"id":"2110.02421","title":"Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective","created":"2021-10-06","cited_by_count":2,"area":null},{"id":"2203.13319","title":"Remember and Forget Experience Replay for Multi-Agent Reinforcement Learning","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2209.07074","title":"On the Reuse Bias in Off-Policy Reinforcement Learning","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2211.16427","title":"Multi-agent reinforcement learning for wall modeling in LES of flow over periodic hills","created":"2022-11-29","cited_by_count":2,"area":null},{"id":"2305.10548","title":"Discovering Individual Rewards in Collective Behavior through Inverse Multi-Agent Reinforcement Learning","created":"2023-05-17","cited_by_count":2,"area":null},{"id":"2203.08937","title":"Backpropagation through Time and Space: Learning Numerical Methods with Multi-Agent Reinforcement Learning","created":"2022-03-16","cited_by_count":1,"area":null},{"id":"2206.13714","title":"Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse","created":"2022-06-28","cited_by_count":1,"area":null},{"id":"2212.13175","title":"Off-Policy Reinforcement Learning with Loss Function Weighted by Temporal Difference Error","created":"2022-12-26","cited_by_count":1,"area":null},{"id":"2404.02171","title":"Optimal navigation of magnetic artificial microswimmers in blood capillaries with deep reinforcement learning","created":"2024-03-29","cited_by_count":1,"area":null},{"id":"2111.06907","title":"Improving Experience Replay through Modeling of Similar Transitions' Sets","created":"2021-11-12","cited_by_count":0,"area":null},{"id":"2209.07758","title":"Game-theoretic Objective Space Planning","created":"2022-09-16","cited_by_count":0,"area":null},{"id":"2507.19298","title":"Controlling Topological Defects in Polar Fluids via Reinforcement Learning","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2602.10430","title":"Breaking the Curse of Repulsion: Remoteness-Aware Control of Negative Off-Policy Updates","created":"2026-02-11","cited_by_count":0,"area":null}],"next_cursor":null}