{"total":18,"rows":[{"id":"2210.05639","title":"Discovered Policy Optimisation","created":"2022-10-11","cited_by_count":104,"area":null},{"id":"2206.05825","title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","created":"2022-06-12","cited_by_count":66,"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":"2201.02373","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","created":"2022-01-07","cited_by_count":31,"area":null},{"id":"2108.05828","title":"A general class of surrogate functions for stable and efficient reinforcement learning","created":"2021-08-12","cited_by_count":18,"area":null},{"id":"2212.13769","title":"Lexicographic Multi-Objective Reinforcement Learning","created":"2022-12-28","cited_by_count":17,"area":null},{"id":"2205.10047","title":"The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure","created":"2022-05-20","cited_by_count":12,"area":null},{"id":"2208.01682","title":"Heterogeneous-Agent Mirror Learning: A Continuum of Solutions to Cooperative MARL","created":"2022-08-02","cited_by_count":12,"area":null},{"id":"2205.11104","title":"Generalization, Mayhems and Limits in Recurrent Proximal Policy Optimization","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2311.02719","title":"Uncertainty Estimation for Safety-critical Scene Segmentation via Fine-grained Reward Maximization","created":"2023-11-05","cited_by_count":7,"area":null},{"id":"2108.02439","title":"Learning to Design and Construct Bridge without Blueprint","created":"2021-08-05","cited_by_count":6,"area":null},{"id":"2210.11262","title":"RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2211.02052","title":"Theta-Resonance: A Single-Step Reinforcement Learning Method for Design Space Exploration","created":"2022-11-03","cited_by_count":4,"area":null},{"id":"2202.12866","title":"Learning to Schedule Heuristics for the Simultaneous Stochastic Optimization of Mining Complexes","created":"2022-02-25","cited_by_count":1,"area":null},{"id":"2312.05405","title":"Guaranteed Trust Region Optimization via Two-Phase KL Penalization","created":"2023-12-08","cited_by_count":1,"area":null},{"id":"2208.09322","title":"Entropy Augmented Reinforcement Learning","created":"2022-08-19","cited_by_count":0,"area":null},{"id":"2601.22532","title":"Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2606.08153","title":"LogNEO: A GPT-Neo Reinforcement Learning Framework for Accurate Real-Time Log Anomaly Detection","created":"2026-06-06","cited_by_count":0,"area":null}],"next_cursor":null}