{"list":"other","total":52,"rows":[{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"1807.03765","title":"Is Q-learning Provably Efficient?","created":"2018-07-10","cited_by_count":487},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"1611.04717","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","created":"2016-11-15","cited_by_count":309},{"id":"2106.05091","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","created":"2021-06-09","cited_by_count":302},{"id":"1905.00360","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","created":"2019-05-01","cited_by_count":287},{"id":"1301.2609","title":"Learning to Optimize Via Posterior Sampling","created":"2013-01-11","cited_by_count":256},{"id":"2006.01107","title":"Model-Based Reinforcement Learning with Value-Targeted Regression","created":"2020-06-01","cited_by_count":234},{"id":"2006.10814","title":"FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs","created":"2020-06-18","cited_by_count":233},{"id":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223},{"id":"1905.10389","title":"Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound","created":"2019-05-24","cited_by_count":201},{"id":"2012.08507","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes","created":"2020-12-15","cited_by_count":200},{"id":"1901.00210","title":"Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds","created":"2019-01-01","cited_by_count":195},{"id":"2003.00153","title":"Learning Near Optimal Policies with Low Inherent Bellman Error","created":"2020-02-29","cited_by_count":181},{"id":"2002.02794","title":"Reward-Free Exploration for Reinforcement Learning","created":"2020-02-07","cited_by_count":177},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","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":"1701.06049","title":"Interactive Learning from Policy-Dependent Human Feedback","created":"2017-01-21","cited_by_count":158},{"id":"1906.03804","title":"Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal","created":"2019-06-10","cited_by_count":127},{"id":"1406.1853","title":"Model-based Reinforcement Learning and the Eluder Dimension","created":"2014-06-07","cited_by_count":116},{"id":"2002.04017","title":"Provable Self-Play Algorithms for Competitive Reinforcement Learning","created":"2020-02-10","cited_by_count":113},{"id":"2010.01604","title":"A Sharp Analysis of Model-based Reinforcement Learning with Self-Play","created":"2020-10-04","cited_by_count":105},{"id":"2006.13165","title":"Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping","created":"2020-06-23","cited_by_count":102},{"id":"2007.13442","title":"Fast active learning for pure exploration in reinforcement learning","created":"2020-07-27","cited_by_count":92},{"id":"2006.11274","title":"On Reward-Free Reinforcement Learning with Linear Function Approximation","created":"2020-06-19","cited_by_count":89},{"id":"2102.07035","title":"Model-free Representation Learning and Exploration in Low-rank MDPs","created":"2021-02-14","cited_by_count":82},{"id":"2006.06294","title":"Adaptive Reward-Free Exploration","created":"2020-06-11","cited_by_count":77},{"id":"2005.02575","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","created":"2020-05-06","cited_by_count":71},{"id":"1910.04365","title":"Asking Easy Questions: A User-Friendly Approach to Active Reward Learning","created":"2019-10-10","cited_by_count":68},{"id":"1309.6821","title":"Sample Complexity of Multi-task Reinforcement Learning","created":"2013-09-26","cited_by_count":58},{"id":"2008.07737","title":"Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration","created":"2020-08-18","cited_by_count":56},{"id":"2201.11206","title":"Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes","created":"2022-01-26","cited_by_count":49},{"id":"1810.11748","title":"DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback","created":"2018-10-28","cited_by_count":41},{"id":"2006.09497","title":"Task-agnostic Exploration in Reinforcement Learning","created":"2020-06-16","cited_by_count":37},{"id":"2005.00527","title":"Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?","created":"2020-05-01","cited_by_count":35},{"id":"2108.05382","title":"Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback","created":"2021-08-11","cited_by_count":35},{"id":"2110.06394","title":"Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation","created":"2021-10-12","cited_by_count":29},{"id":"2206.10770","title":"On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL","created":"2022-06-21","cited_by_count":27},{"id":"2102.12466","title":"Information Directed Reward Learning for Reinforcement Learning","created":"2021-02-24","cited_by_count":24},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24},{"id":"2005.04067","title":"Active Preference Learning using Maximum Regret","created":"2020-05-08","cited_by_count":21},{"id":"1811.02619","title":"State Aggregation Learning from Markov Transition Data","created":"2018-11-06","cited_by_count":20},{"id":"2110.09771","title":"On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game","created":"2021-10-19","cited_by_count":20},{"id":"2111.00633","title":"Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning","created":"2021-11-01","cited_by_count":18},{"id":"2105.06029","title":"Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings","created":"2021-05-13","cited_by_count":14},{"id":"2011.13034","title":"Accommodating Picky Customers: Regret Bound and Exploration Complexity for Multi-Objective Reinforcement Learning","created":"2020-11-25","cited_by_count":11},{"id":"2108.05439","title":"Gap-Dependent Unsupervised Exploration for Reinforcement Learning","created":"2021-08-11","cited_by_count":10}],"next_cursor":null}