{"list":"other","total":51,"rows":[{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"id":"1910.01741","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","created":"2019-10-02","cited_by_count":274},{"id":"1611.07507","title":"Variational Intrinsic Control","created":"2016-11-22","cited_by_count":267},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1812.02690","title":"Provably Efficient Maximum Entropy Exploration","created":"2018-12-06","cited_by_count":242},{"id":"2010.11944","title":"Accelerating Reinforcement Learning with Learned Skill Priors","created":"2020-10-22","cited_by_count":223},{"id":"2102.11271","title":"Reinforcement Learning with Prototypical Representations","created":"2021-02-22","cited_by_count":179},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"2103.04551","title":"Behavior From the Void: Unsupervised Active Pre-Training","created":"2021-03-08","cited_by_count":174},{"id":"2110.15191","title":"URLB: Unsupervised Reinforcement Learning Benchmark","created":"2021-10-28","cited_by_count":139},{"id":"1906.05030","title":"Fast Task Inference with Variational Intrinsic Successor Features","created":"2019-06-12","cited_by_count":133},{"id":"2104.07749","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","created":"2021-04-15","cited_by_count":125},{"id":"1509.01149","title":"Model Predictive Path Integral Control using Covariance Variable Importance Sampling","created":"2015-09-03","cited_by_count":124},{"id":"2002.03647","title":"Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills","created":"2020-02-10","cited_by_count":122},{"id":"1811.01848","title":"Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control","created":"2018-11-05","cited_by_count":113},{"id":"2108.13956","title":"APS: Active Pretraining with Successor Features","created":"2021-08-31","cited_by_count":112},{"id":"2102.09430","title":"State Entropy Maximization with Random Encoders for Efficient Exploration","created":"2021-02-18","cited_by_count":108},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108},{"id":"1906.08649","title":"Exploring Model-based Planning with Policy Networks","created":"2019-06-20","cited_by_count":90},{"id":"2202.00161","title":"CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery","created":"2022-02-01","cited_by_count":68},{"id":"2202.01741","title":"How to Leverage Unlabeled Data in Offline Reinforcement Learning","created":"2022-02-03","cited_by_count":62},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58},{"id":"2008.10066","title":"Learning Off-Policy with Online Planning","created":"2020-08-23","cited_by_count":53},{"id":"1911.07450","title":"Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation","created":"2019-11-18","cited_by_count":40},{"id":"2007.01995","title":"Bidirectional Model-based Policy Optimization","created":"2020-07-04","cited_by_count":38},{"id":"2010.04893","title":"Trust the Model When It Is Confident: Masked Model-based Actor-Critic","created":"2020-10-10","cited_by_count":36},{"id":"2010.13303","title":"Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning","created":"2020-10-26","cited_by_count":35},{"id":"1706.03475","title":"Confident Multiple Choice Learning","created":"2017-06-12","cited_by_count":24},{"id":"2203.08553","title":"PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration","created":"2022-03-16","cited_by_count":23},{"id":"2104.07495","title":"Curiosity-Driven Exploration via Latent Bayesian Surprise","created":"2021-04-15","cited_by_count":22},{"id":"2205.11051","title":"Flow-based Recurrent Belief State Learning for POMDPs","created":"2022-05-23","cited_by_count":16},{"id":"1910.13038","title":"Learning to Predict Without Looking Ahead: World Models Without Forward Prediction","created":"2019-10-29","cited_by_count":15},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13},{"id":"2012.10716","title":"Model-Based Actor-Critic with Chance Constraint for Stochastic System","created":"2020-12-19","cited_by_count":9},{"id":"1910.09134","title":"Good, Better, Best: Textual Distractors Generation for Multiple-Choice Visual Question Answering via Reinforcement Learning","created":"2019-10-21","cited_by_count":6},{"id":"2205.01906","title":"ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters","created":"2022-05-04","cited_by_count":6},{"id":"1903.01567","title":"Model Primitive Hierarchical Lifelong Reinforcement Learning","created":"2019-03-04","cited_by_count":5},{"id":"1405.7361","title":"Seeking multi-thresholds for image segmentation with Learning Automata","created":"2014-05-28","cited_by_count":1}],"next_cursor":null}