{"list":"other","total":54,"rows":[{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"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":"2002.02794","title":"Reward-Free Exploration for Reinforcement Learning","created":"2020-02-07","cited_by_count":177},{"id":"1703.07710","title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","created":"2017-03-22","cited_by_count":176},{"id":"2004.10019","title":"Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition","created":"2020-04-21","cited_by_count":127},{"id":"2101.02195","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints","created":"2021-01-06","cited_by_count":124},{"id":"2110.14555","title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL","created":"2021-10-27","cited_by_count":114},{"id":"2002.04017","title":"Provable Self-Play Algorithms for Competitive Reinforcement Learning","created":"2020-02-10","cited_by_count":113},{"id":"2006.12007","title":"Near-Optimal Reinforcement Learning with Self-Play","created":"2020-06-22","cited_by_count":109},{"id":"2010.01604","title":"A Sharp Analysis of Model-based Reinforcement Learning with Self-Play","created":"2020-10-04","cited_by_count":105},{"id":"2002.07066","title":"Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium","created":"2020-02-17","cited_by_count":100},{"id":"1904.01763","title":"Batched Multi-armed Bandits Problem","created":"2019-04-03","cited_by_count":98},{"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":"1811.03056","title":"Policy Certificates: Towards Accountable Reinforcement Learning","created":"2018-11-07","cited_by_count":81},{"id":"1905.12849","title":"Provably Efficient Q-Learning with Low Switching Cost","created":"2019-05-30","cited_by_count":78},{"id":"2011.12692","title":"Towards Playing Full MOBA Games with Deep Reinforcement Learning","created":"2020-11-25","cited_by_count":78},{"id":"2006.06294","title":"Adaptive Reward-Free Exploration","created":"2020-06-11","cited_by_count":77},{"id":"2004.06321","title":"Sequential Batch Learning in Finite-Action Linear Contextual Bandits","created":"2020-04-14","cited_by_count":63},{"id":"1302.4387","title":"Online Learning with Switching Costs and Other Adaptive Adversaries","created":"2013-02-18","cited_by_count":61},{"id":"2212.06132","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes","created":"2022-12-12","cited_by_count":57},{"id":"2008.07737","title":"Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration","created":"2020-08-18","cited_by_count":56},{"id":"2007.01980","title":"Linear Bandits with Limited Adaptivity and Learning Distributional Optimal Design","created":"2020-07-04","cited_by_count":51},{"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":"2106.03352","title":"The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces","created":"2021-06-07","cited_by_count":48},{"id":"2107.14702","title":"Towards General Function Approximation in Zero-Sum Markov Games","created":"2021-07-30","cited_by_count":43},{"id":"2101.00494","title":"A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost","created":"2021-01-02","cited_by_count":40},{"id":"2006.09497","title":"Task-agnostic Exploration in Reinforcement Learning","created":"2020-06-16","cited_by_count":37},{"id":"2110.05707","title":"On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning","created":"2021-10-12","cited_by_count":36},{"id":"2202.06385","title":"Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost","created":"2022-02-13","cited_by_count":32},{"id":"2107.05216","title":"A Simple Reward-free Approach to Constrained Reinforcement Learning","created":"2021-07-12","cited_by_count":30},{"id":"2302.06606","title":"Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation","created":"2023-02-13","cited_by_count":30},{"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":"2302.03673","title":"Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation","created":"2023-02-07","cited_by_count":27},{"id":"2010.05901","title":"Nearly Minimax Optimal Reward-free Reinforcement Learning","created":"2020-10-12","cited_by_count":26},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24},{"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":"2212.04680","title":"Near-Optimal Differentially Private Reinforcement Learning","created":"2022-12-09","cited_by_count":16},{"id":"2304.07278","title":"Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning","created":"2023-04-14","cited_by_count":15},{"id":"2110.03244","title":"Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver","created":"2021-10-07","cited_by_count":14},{"id":"2311.15238","title":"A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation","created":"2023-11-26","cited_by_count":14},{"id":"2210.00701","title":"Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation","created":"2022-10-03","cited_by_count":13},{"id":"2210.08238","title":"Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning","created":"2022-10-15","cited_by_count":13},{"id":"2006.16100","title":"Distributed Deep Reinforcement Learning for Intelligent Load Scheduling in Residential Smart Grids","created":"2020-06-29","cited_by_count":11},{"id":"2302.12456","title":"Logarithmic Switching Cost in Reinforcement Learning beyond Linear MDPs","created":"2023-02-24","cited_by_count":9},{"id":"2209.11837","title":"Doubly Fair Dynamic Pricing","created":"2022-09-23","cited_by_count":8},{"id":"2305.15546","title":"Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time","created":"2023-05-24","cited_by_count":8},{"id":"2302.01477","title":"A Reduction-based Framework for Sequential Decision Making with Delayed Feedback","created":"2023-02-03","cited_by_count":7},{"id":"2306.14468","title":"A General Framework for Sequential Decision-Making under Adaptivity Constraints","created":"2023-06-26","cited_by_count":6},{"id":"2302.04374","title":"Near-Optimal Adversarial Reinforcement Learning with Switching Costs","created":"2023-02-08","cited_by_count":4},{"id":"2310.01616","title":"Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity","created":"2023-10-02","cited_by_count":2}],"next_cursor":null}