{"list":"other","total":53,"rows":[{"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":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"1610.09512","title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","created":"2016-10-29","cited_by_count":292},{"id":"2106.06926","title":"Bellman-consistent Pessimism for Offline Reinforcement Learning","created":"2021-06-13","cited_by_count":269},{"id":"1707.04175","title":"Distral: Robust Multitask Reinforcement Learning","created":"2017-07-13","cited_by_count":233},{"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":"2002.09434","title":"Few-Shot Learning via Learning the Representation, Provably","created":"2020-02-21","cited_by_count":214},{"id":"1912.05830","title":"Provably Efficient Exploration in Policy Optimization","created":"2019-12-12","cited_by_count":205},{"id":"1905.10389","title":"Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound","created":"2019-05-24","cited_by_count":201},{"id":"1505.06279","title":"The Benefit of Multitask Representation Learning","created":"2015-05-23","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":"2103.10897","title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL","created":"2021-03-19","cited_by_count":178},{"id":"1703.07710","title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","created":"2017-03-22","cited_by_count":176},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174},{"id":"1901.09018","title":"Provably efficient RL with Rich Observations via Latent State Decoding","created":"2019-01-25","cited_by_count":169},{"id":"2002.11684","title":"Provable Meta-Learning of Linear Representations","created":"2020-02-26","cited_by_count":161},{"id":"2106.04895","title":"Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning","created":"2021-06-09","cited_by_count":158},{"id":"2010.11895","title":"What are the Statistical Limits of Offline RL with Linear Function Approximation?","created":"2020-10-22","cited_by_count":136},{"id":"2110.04652","title":"Representation Learning for Online and Offline RL in Low-rank MDPs","created":"2021-10-09","cited_by_count":129},{"id":"1911.05815","title":"Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning","created":"2019-11-13","cited_by_count":114},{"id":"1402.0635","title":"Generalization and Exploration via Randomized Value Functions","created":"2014-02-04","cited_by_count":112},{"id":"1912.04136","title":"Optimism in Reinforcement Learning with Generalized Linear Function Approximation","created":"2019-12-09","cited_by_count":111},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110},{"id":"2102.07035","title":"Model-free Representation Learning and Exploration in Low-rank MDPs","created":"2021-02-14","cited_by_count":82},{"id":"2110.08695","title":"Towards Instance-Optimal Offline Reinforcement Learning with Pessimism","created":"2021-10-17","cited_by_count":78},{"id":"2203.05804","title":"Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism","created":"2022-03-11","cited_by_count":65},{"id":"1309.6821","title":"Sample Complexity of Multi-task Reinforcement Learning","created":"2013-09-26","cited_by_count":58},{"id":"1710.09988","title":"Variance Reduced Value Iteration and Faster Algorithms for Solving Markov Decision Processes","created":"2017-10-27","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":"2012.08005","title":"Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL","created":"2020-12-14","cited_by_count":55},{"id":"2205.15512","title":"Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game","created":"2022-05-31","cited_by_count":55},{"id":"2007.01891","title":"A Unifying View of Optimism in Episodic Reinforcement Learning","created":"2020-07-03","cited_by_count":52},{"id":"2010.06531","title":"Impact of Representation Learning in Linear Bandits","created":"2020-10-13","cited_by_count":52},{"id":"2202.00063","title":"Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach","created":"2022-01-31","cited_by_count":51},{"id":"1705.08618","title":"Multi-Task Learning for Contextual Bandits","created":"2017-05-24","cited_by_count":47},{"id":"2102.04132","title":"Near-optimal Representation Learning for Linear Bandits and Linear RL","created":"2021-02-08","cited_by_count":45},{"id":"2002.08936","title":"Meta-learning for mixed linear regression","created":"2020-02-20","cited_by_count":44},{"id":"2002.10544","title":"Provable Representation Learning for Imitation Learning via Bi-level Optimization","created":"2020-02-24","cited_by_count":41},{"id":"2205.14571","title":"Provable Benefits of Representational Transfer in Reinforcement Learning","created":"2022-05-29","cited_by_count":38},{"id":"2103.14077","title":"Nearly Horizon-Free Offline Reinforcement Learning","created":"2021-03-25","cited_by_count":36},{"id":"2106.11960","title":"Variance-Aware Off-Policy Evaluation with Linear Function Approximation","created":"2021-06-22","cited_by_count":34},{"id":"2106.08053","title":"On the Power of Multitask Representation Learning in Linear MDP","created":"2021-06-15","cited_by_count":30},{"id":"2202.10066","title":"Multi-task Representation Learning with Stochastic Linear Bandits","created":"2022-02-21","cited_by_count":21},{"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":"2201.04805","title":"Non-Stationary Representation Learning in Sequential Linear Bandits","created":"2022-01-13","cited_by_count":13},{"id":"2205.15701","title":"Provable General Function Class Representation Learning in Multitask Bandits and MDPs","created":"2022-05-31","cited_by_count":12},{"id":"2202.11960","title":"All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL","created":"2022-02-24","cited_by_count":9},{"id":"2202.13001","title":"Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms","created":"2022-02-25","cited_by_count":8},{"id":"2201.08732","title":"Meta Learning MDPs with Linear Transition Models","created":"2022-01-21","cited_by_count":4}],"next_cursor":null}