{"total":9,"rows":[{"id":"2206.00730","title":"The Phenomenon of Policy Churn","created":"2022-06-01","cited_by_count":28,"area":null},{"id":"2207.07570","title":"The Nature of Temporal Difference Errors in Multi-step Distributional Reinforcement Learning","created":"2022-07-15","cited_by_count":10,"area":null},{"id":"2301.11321","title":"Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning","created":"2023-01-26","cited_by_count":6,"area":null},{"id":"2209.12347","title":"Opportunities and Challenges from Using Animal Videos in Reinforcement Learning for Navigation","created":"2022-09-25","cited_by_count":4,"area":null},{"id":"2206.05910","title":"Safe-FinRL: A Low Bias and Variance Deep Reinforcement Learning Implementation for High-Freq Stock Trading","created":"2022-06-13","cited_by_count":1,"area":null},{"id":"2402.05766","title":"Off-policy Distributional Q($\\lambda$): Distributional RL without Importance Sampling","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2112.03421","title":"Virtual Replay Cache","created":"2021-12-06","cited_by_count":0,"area":null},{"id":"2112.12281","title":"Improving the Efficiency of Off-Policy Reinforcement Learning by Accounting for Past Decisions","created":"2021-12-23","cited_by_count":0,"area":null},{"id":"2203.03292","title":"On Credit Assignment in Hierarchical Reinforcement Learning","created":"2022-03-07","cited_by_count":0,"area":null}],"next_cursor":null}