{"list":"other","total":54,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"1912.02074","title":"AlgaeDICE: Policy Gradient from Arbitrary Experience","created":"2019-12-04","cited_by_count":188},{"id":"1812.02648","title":"Deep Reinforcement Learning and the Deadly Triad","created":"2018-12-06","cited_by_count":174},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174},{"id":"2005.04269","title":"Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics","created":"2020-05-08","cited_by_count":165},{"id":"2010.14498","title":"Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning","created":"2020-10-27","cited_by_count":134},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125},{"id":"2009.04416","title":"Phasic Policy Gradient","created":"2020-09-09","cited_by_count":123},{"id":"2002.09072","title":"GenDICE: Generalized Offline Estimation of Stationary Values","created":"2020-02-21","cited_by_count":122},{"id":"2106.10783","title":"OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation","created":"2021-06-21","cited_by_count":121},{"id":"2303.07507","title":"Loss of Plasticity in Continual Deep Reinforcement Learning","created":"2023-03-13","cited_by_count":121},{"id":"2002.06487","title":"Maxmin Q-learning: Controlling the Estimation Bias of Q-learning","created":"2020-02-16","cited_by_count":117},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82},{"id":"2006.05826","title":"Transient Non-Stationarity and Generalisation in Deep Reinforcement Learning","created":"2020-06-10","cited_by_count":75},{"id":"2003.07305","title":"DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction","created":"2020-03-16","cited_by_count":71},{"id":"2112.04716","title":"DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization","created":"2021-12-09","cited_by_count":66},{"id":"2006.02243","title":"The Value-Improvement Path: Towards Better Representations for Reinforcement Learning","created":"2020-06-03","cited_by_count":60},{"id":"2110.14020","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","created":"2021-10-26","cited_by_count":50},{"id":"2403.00514","title":"Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning","created":"2024-03-01","cited_by_count":50},{"id":"2101.08862","title":"Breaking the Deadly Triad with a Target Network","created":"2021-01-21","cited_by_count":47},{"id":"2310.19668","title":"DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization","created":"2023-10-30","cited_by_count":47},{"id":"1903.08894","title":"Towards Characterizing Divergence in Deep Q-Learning","created":"2019-03-21","cited_by_count":43},{"id":"2306.13812","title":"Maintaining Plasticity in Deep Continual Learning","created":"2023-06-23","cited_by_count":43},{"id":"2003.06350","title":"Interference and Generalization in Temporal Difference Learning","created":"2020-03-13","cited_by_count":42},{"id":"2003.01629","title":"Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?","created":"2020-03-03","cited_by_count":37},{"id":"2109.05490","title":"HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation","created":"2021-09-12","cited_by_count":35},{"id":"2203.02628","title":"Target Network and Truncation Overcome The Deadly Triad in $Q$-Learning","created":"2022-03-05","cited_by_count":31},{"id":"2206.00730","title":"The Phenomenon of Policy Churn","created":"2022-06-01","cited_by_count":28},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28},{"id":"1903.03176","title":"MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments","created":"2019-03-07","cited_by_count":19},{"id":"2206.04672","title":"Overcoming the Spectral Bias of Neural Value Approximation","created":"2022-06-09","cited_by_count":19},{"id":"2003.07417","title":"Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks","created":"2020-03-16","cited_by_count":17},{"id":"2205.10868","title":"Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation","created":"2022-05-22","cited_by_count":9},{"id":"2106.02613","title":"Bridging the Gap Between Target Networks and Functional Regularization","created":"2021-06-04","cited_by_count":7},{"id":"2007.03807","title":"Towards a practical measure of interference for reinforcement learning","created":"2020-07-07","cited_by_count":6},{"id":"2307.04887","title":"Measuring and Mitigating Interference in Reinforcement Learning","created":"2023-07-10","cited_by_count":5},{"id":"2002.12399","title":"ConQUR: Mitigating Delusional Bias in Deep Q-learning","created":"2020-02-27","cited_by_count":4}],"next_cursor":null}