{"list":"other","total":73,"rows":[{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"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":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"1604.00923","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","created":"2016-04-04","cited_by_count":286},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279},{"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":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","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":"1910.12809","title":"Minimax Weight and Q-Function Learning for Off-Policy Evaluation","created":"2019-10-28","cited_by_count":150},{"id":"2004.10019","title":"Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition","created":"2020-04-21","cited_by_count":127},{"id":"2002.09516","title":"Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation","created":"2020-02-21","cited_by_count":120},{"id":"1908.08526","title":"Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes","created":"2019-08-22","cited_by_count":119},{"id":"2301.08028","title":"A Tutorial on Meta-Reinforcement Learning","created":"2023-01-19","cited_by_count":108},{"id":"2010.03531","title":"Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited","created":"2020-10-07","cited_by_count":106},{"id":"2009.13503","title":"Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon","created":"2020-09-28","cited_by_count":99},{"id":"2006.13916","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","created":"2020-06-24","cited_by_count":97},{"id":"2007.07461","title":"Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity","created":"2020-07-15","cited_by_count":92},{"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":"2007.03438","title":"Off-Policy Evaluation via the Regularized Lagrangian","created":"2020-07-07","cited_by_count":86},{"id":"2112.01506","title":"Sample Complexity of Robust Reinforcement Learning with a Generative Model","created":"2021-12-02","cited_by_count":83},{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80},{"id":"1905.12849","title":"Provably Efficient Q-Learning with Low Switching Cost","created":"2019-05-30","cited_by_count":78},{"id":"2006.06294","title":"Adaptive Reward-Free Exploration","created":"2020-06-11","cited_by_count":77},{"id":"1906.04697","title":"Variance-reduced $Q$-learning is minimax optimal","created":"2019-06-11","cited_by_count":73},{"id":"1308.3513","title":"Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations","created":"2013-08-15","cited_by_count":70},{"id":"2102.04939","title":"RL for Latent MDPs: Regret Guarantees and a Lower Bound","created":"2021-02-09","cited_by_count":70},{"id":"2006.09118","title":"$Q$-learning with Logarithmic Regret","created":"2020-06-16","cited_by_count":60},{"id":"2206.13464","title":"When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning","created":"2022-06-27","cited_by_count":60},{"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":"1901.09311","title":"Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP","created":"2019-01-27","cited_by_count":55},{"id":"2305.16589","title":"The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model","created":"2023-05-26","cited_by_count":52},{"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":"2103.01312","title":"UCB Momentum Q-learning: Correcting the bias without forgetting","created":"2021-03-01","cited_by_count":46},{"id":"1803.01626","title":"Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs","created":"2018-03-05","cited_by_count":43},{"id":"2010.00587","title":"Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs","created":"2020-10-01","cited_by_count":42},{"id":"2203.06662","title":"DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning","created":"2022-03-13","cited_by_count":41},{"id":"2103.14077","title":"Nearly Horizon-Free Offline Reinforcement Learning","created":"2021-03-25","cited_by_count":36},{"id":"2006.05879","title":"Planning in Markov Decision Processes with Gap-Dependent Sample Complexity","created":"2020-06-10","cited_by_count":34},{"id":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32},{"id":"1807.09647","title":"Variational Bayesian Reinforcement Learning with Regret Bounds","created":"2018-07-25","cited_by_count":31},{"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":"2007.03760","title":"Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning","created":"2020-07-07","cited_by_count":26},{"id":"2109.12002","title":"Optimal policy evaluation using kernel-based temporal difference methods","created":"2021-09-24","cited_by_count":24},{"id":"2004.05599","title":"Kernel-Based Reinforcement Learning: A Finite-Time Analysis","created":"2020-04-12","cited_by_count":23},{"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":"2002.05138","title":"Regret Bounds for Discounted MDPs","created":"2020-02-12","cited_by_count":19},{"id":"2403.09621","title":"Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning","created":"2024-03-14","cited_by_count":18},{"id":"2405.06192","title":"Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning","created":"2024-05-10","cited_by_count":18},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17},{"id":"2309.12716","title":"H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps","created":"2023-09-22","cited_by_count":17},{"id":"2305.10282","title":"Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning","created":"2023-05-17","cited_by_count":16},{"id":"2402.04580","title":"A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents","created":"2024-02-07","cited_by_count":16},{"id":"2403.12946","title":"Sample Complexity of Offline Distributionally Robust Linear Markov Decision Processes","created":"2024-03-19","cited_by_count":14},{"id":"2209.08230","title":"A Robust and Constrained Multi-Agent Reinforcement Learning Electric Vehicle Rebalancing Method in AMoD Systems","created":"2022-09-17","cited_by_count":11},{"id":"2307.04354","title":"Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data","created":"2023-07-10","cited_by_count":11},{"id":"1612.00147","title":"Combining Deep Reinforcement Learning and Safety Based Control for Autonomous Driving","created":"2016-12-01","cited_by_count":9},{"id":"2006.04354","title":"A Model-free Learning Algorithm for Infinite-horizon Average-reward MDPs with Near-optimal Regret","created":"2020-06-08","cited_by_count":7},{"id":"2210.10464","title":"On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness","created":"2022-10-19","cited_by_count":7},{"id":"2110.09507","title":"Provable Hierarchy-Based Meta-Reinforcement Learning","created":"2021-10-18","cited_by_count":5},{"id":"2406.02282","title":"Test-Time Regret Minimization in Meta Reinforcement Learning","created":"2024-06-04","cited_by_count":5},{"id":"2408.12136","title":"Provable Domain Adaptation for Offline Reinforcement Learning with Limited Samples","created":"2024-08-22","cited_by_count":5},{"id":"1409.3653","title":"On Minimax Optimal Offline Policy Evaluation","created":"2014-09-12","cited_by_count":4},{"id":"2312.03764","title":"Similarity-based Knowledge Transfer for Cross-Domain Reinforcement Learning","created":"2023-12-05","cited_by_count":4},{"id":"2107.02711","title":"A Unified Off-Policy Evaluation Approach for General Value Function","created":"2021-07-06","cited_by_count":1}],"next_cursor":null}