{"list":"other","total":56,"rows":[{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"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":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"id":"1804.08617","title":"Distributed Distributional Deterministic Policy Gradients","created":"2018-04-23","cited_by_count":199},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","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":"2007.04938","title":"SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning","created":"2020-07-09","cited_by_count":152},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147},{"id":"2202.04634","title":"Offline Reinforcement Learning with Realizability and Single-policy Concentrability","created":"2022-02-09","cited_by_count":123},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114},{"id":"1912.04136","title":"Optimism in Reinforcement Learning with Generalized Linear Function Approximation","created":"2019-12-09","cited_by_count":111},{"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":"1910.12807","title":"Better Exploration with Optimistic Actor-Critic","created":"2019-10-28","cited_by_count":88},{"id":"2208.07860","title":"A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning","created":"2022-08-16","cited_by_count":83},{"id":"2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","created":"2022-10-09","cited_by_count":83},{"id":"2003.07305","title":"DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction","created":"2020-03-16","cited_by_count":71},{"id":"2111.10919","title":"Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation","created":"2021-11-21","cited_by_count":71},{"id":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65},{"id":"2102.03765","title":"Tactical Optimism and Pessimism for Deep Reinforcement Learning","created":"2021-02-07","cited_by_count":55},{"id":"1911.03618","title":"Worst Cases Policy Gradients","created":"2019-11-09","cited_by_count":52},{"id":"2007.01891","title":"A Unifying View of Optimism in Episodic Reinforcement Learning","created":"2020-07-03","cited_by_count":52},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40},{"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},{"id":"2304.10466","title":"Efficient Deep Reinforcement Learning Requires Regulating Overfitting","created":"2023-04-20","cited_by_count":36},{"id":"2002.02693","title":"Ready Policy One: World Building Through Active Learning","created":"2020-02-07","cited_by_count":33},{"id":"1801.03326","title":"Expected Policy Gradients for Reinforcement Learning","created":"2018-01-10","cited_by_count":28},{"id":"2107.08966","title":"Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration","created":"2021-07-19","cited_by_count":25},{"id":"2110.03375","title":"Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning","created":"2021-10-07","cited_by_count":18},{"id":"1905.09191","title":"Learning Robust Options by Conditional Value at Risk Optimization","created":"2019-05-22","cited_by_count":16},{"id":"2010.14641","title":"Learning to Plan Optimistically: Uncertainty-Guided Deep Exploration via Latent Model Ensembles","created":"2020-10-27","cited_by_count":14},{"id":"2206.00702","title":"Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search","created":"2022-06-01","cited_by_count":12}],"next_cursor":null}