{"list":"other","total":58,"rows":[{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288},{"id":"1901.11275","title":"A Theory of Regularized Markov Decision Processes","created":"2019-01-31","cited_by_count":286},{"id":"1812.03201","title":"Residual Reinforcement Learning for Robot Control","created":"2018-12-07","cited_by_count":274},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"2405.10369","title":"Reinforcement learning","created":"2024-05-16","cited_by_count":247},{"id":"1812.02648","title":"Deep Reinforcement Learning and the Deadly Triad","created":"2018-12-06","cited_by_count":174},{"id":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"2007.04938","title":"SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning","created":"2020-07-09","cited_by_count":152},{"id":"2403.03950","title":"Stop Regressing: Training Value Functions via Classification for Scalable Deep RL","created":"2024-03-06","cited_by_count":144},{"id":"1512.08562","title":"Taming the Noise in Reinforcement Learning via Soft Updates","created":"2015-12-28","cited_by_count":127},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114},{"id":"2405.16158","title":"Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control","created":"2024-05-25","cited_by_count":108},{"id":"1902.05605","title":"CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity","created":"2019-02-14","cited_by_count":95},{"id":"1708.04133","title":"Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control","created":"2017-08-10","cited_by_count":93},{"id":"1910.12807","title":"Better Exploration with Optimistic Actor-Critic","created":"2019-10-28","cited_by_count":88},{"id":"2402.18762","title":"Disentangling the Causes of Plasticity Loss in Neural Networks","created":"2024-02-29","cited_by_count":86},{"id":"1709.05380","title":"The Uncertainty Bellman Equation and Exploration","created":"2017-09-15","cited_by_count":82},{"id":"1806.08295","title":"How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments","created":"2018-06-21","cited_by_count":60},{"id":"2102.03765","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","created":"2021-02-07","cited_by_count":55},{"id":"1912.05663","title":"Measuring the Reliability of Reinforcement Learning Algorithms","created":"2019-12-10","cited_by_count":51},{"id":"2201.08430","title":"Reproducibility in Learning","created":"2022-01-20","cited_by_count":44},{"id":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41},{"id":"2502.15280","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","created":"2025-02-21","cited_by_count":38},{"id":"1905.05380","title":"Control Regularization for Reduced Variance Reinforcement Learning","created":"2019-05-14","cited_by_count":37},{"id":"2304.10466","title":"Efficient Deep Reinforcement Learning Requires Regulating Overfitting","created":"2023-04-20","cited_by_count":36},{"id":"2110.11222","title":"Is High Variance Unavoidable in RL? A Case Study in Continuous Control","created":"2021-10-21","cited_by_count":28},{"id":"2206.00730","title":"The Phenomenon of Policy Churn","created":"2022-06-01","cited_by_count":28},{"id":"2305.15284","title":"Replicable Reinforcement Learning","created":"2023-05-24","cited_by_count":21},{"id":"2305.19562","title":"Replicability in Reinforcement Learning","created":"2023-05-31","cited_by_count":21},{"id":"2502.07523","title":"Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization","created":"2025-02-11","cited_by_count":19},{"id":"1909.05950","title":"Mutual-Information Regularization in Markov Decision Processes and Actor-Critic Learning","created":"2019-09-11","cited_by_count":18},{"id":"2403.05996","title":"Dissecting Deep RL with High Update Ratios: Combatting Value Divergence","created":"2024-03-09","cited_by_count":17},{"id":"2409.04792","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","created":"2024-09-07","cited_by_count":17},{"id":"2509.25174","title":"XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning","created":"2025-09-29","cited_by_count":17},{"id":"2410.08896","title":"MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL","created":"2024-10-11","cited_by_count":16},{"id":"2406.16241","title":"Position: Benchmarking is Limited in Reinforcement Learning Research","created":"2024-06-23","cited_by_count":15},{"id":"2406.17718","title":"When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning","created":"2024-06-25","cited_by_count":14},{"id":"1909.03772","title":"A Survey on Reproducibility by Evaluating Deep Reinforcement Learning Algorithms on Real-World Robots","created":"2019-09-09","cited_by_count":12},{"id":"1904.06312","title":"Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments","created":"2019-04-12","cited_by_count":11},{"id":"2410.08870","title":"Can we hop in general? A discussion of benchmark selection and design using the Hopper environment","created":"2024-10-11","cited_by_count":7},{"id":"2501.08669","title":"SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning","created":"2025-01-15","cited_by_count":7},{"id":"2507.11926","title":"From Generative to Episodic: Sample-Efficient Replicable Reinforcement Learning","created":"2025-07-16","cited_by_count":4},{"id":"2312.07178","title":"Beyond Expected Return: Accounting for Policy Reproducibility when Evaluating Reinforcement Learning Algorithms","created":"2023-12-12","cited_by_count":3}],"next_cursor":null}