{"list":"other","total":79,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"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":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"id":"1702.02284","title":"Adversarial Attacks on Neural Network Policies","created":"2017-02-08","cited_by_count":320},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"1611.04201","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","created":"2016-11-13","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":"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":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187},{"id":"1703.07710","title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","created":"2017-03-22","cited_by_count":176},{"id":"1506.02188","title":"Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach","created":"2015-06-06","cited_by_count":170},{"id":"1703.06748","title":"Tactics of Adversarial Attack on Deep Reinforcement Learning Agents","created":"2017-03-08","cited_by_count":166},{"id":"1712.03632","title":"Robust Deep Reinforcement Learning with Adversarial Attacks","created":"2017-12-11","cited_by_count":154},{"id":"1610.01283","title":"EPOpt: Learning Robust Neural Network Policies Using Model Ensembles","created":"2016-10-05","cited_by_count":138},{"id":"2004.10019","title":"Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition","created":"2020-04-21","cited_by_count":127},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116},{"id":"2010.03531","title":"Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited","created":"2020-10-07","cited_by_count":106},{"id":"1705.06452","title":"Delving into adversarial attacks on deep policies","created":"2017-05-18","cited_by_count":104},{"id":"1807.01473","title":"Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation","created":"2018-07-04","cited_by_count":101},{"id":"1404.3862","title":"Optimizing the CVaR via Sampling","created":"2014-04-15","cited_by_count":99},{"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":"2407.13734","title":"Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review","created":"2024-07-18","cited_by_count":98},{"id":"2006.13916","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","created":"2020-06-24","cited_by_count":97},{"id":"2109.14523","title":"Online Robust Reinforcement Learning with Model Uncertainty","created":"2021-09-29","cited_by_count":96},{"id":"2208.05129","title":"Robust Reinforcement Learning using Offline Data","created":"2022-08-10","cited_by_count":96},{"id":"2102.06548","title":"Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis","created":"2021-02-12","cited_by_count":92},{"id":"2208.05767","title":"Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity","created":"2022-08-11","cited_by_count":87},{"id":"2112.01506","title":"Sample Complexity of Robust Reinforcement Learning with a Generative Model","created":"2021-12-02","cited_by_count":83},{"id":"2204.05275","title":"Settling the Sample Complexity of Model-Based Offline Reinforcement Learning","created":"2022-04-11","cited_by_count":83},{"id":"1811.03056","title":"Policy Certificates: Towards Accountable Reinforcement Learning","created":"2018-11-07","cited_by_count":81},{"id":"2401.12244","title":"Large-scale Reinforcement Learning for Diffusion Models","created":"2024-01-20","cited_by_count":78},{"id":"1911.08689","title":"Corruption-robust exploration in episodic reinforcement learning","created":"2019-11-20","cited_by_count":72},{"id":"2205.07344","title":"Policy Gradient Method For Robust Reinforcement Learning","created":"2022-05-15","cited_by_count":69},{"id":"1707.02267","title":"Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task","created":"2017-07-07","cited_by_count":66},{"id":"2008.01825","title":"Robust Reinforcement Learning using Adversarial Populations","created":"2020-08-04","cited_by_count":66},{"id":"2106.06135","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","created":"2021-06-11","cited_by_count":66},{"id":"1907.13196","title":"Wasserstein Robust Reinforcement Learning","created":"2019-07-30","cited_by_count":54},{"id":"2110.04645","title":"Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning","created":"2021-10-09","cited_by_count":53},{"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":"2106.06630","title":"Corruption-Robust Offline Reinforcement Learning","created":"2021-06-11","cited_by_count":51},{"id":"2305.09659","title":"Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage","created":"2023-05-16","cited_by_count":51},{"id":"2103.01312","title":"UCB Momentum Q-learning: Correcting the bias without forgetting","created":"2021-03-01","cited_by_count":46},{"id":"2211.01962","title":"GEC: A Unified Framework for Interactive Decision Making in MDP, POMDP, and Beyond","created":"2022-11-03","cited_by_count":46},{"id":"2110.03580","title":"A Model Selection Approach for Corruption Robust Reinforcement Learning","created":"2021-10-07","cited_by_count":45},{"id":"2307.13586","title":"Settling the Sample Complexity of Online Reinforcement Learning","created":"2023-07-25","cited_by_count":45},{"id":"2303.02783","title":"Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learning","created":"2023-03-05","cited_by_count":44},{"id":"2302.13203","title":"A Finite Sample Complexity Bound for Distributionally Robust Q-learning","created":"2023-02-26","cited_by_count":36},{"id":"2212.05949","title":"Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes","created":"2022-12-12","cited_by_count":33},{"id":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32},{"id":"2310.14550","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","created":"2023-10-23","cited_by_count":31},{"id":"2305.18420","title":"Sample Complexity of Variance-reduced Distributionally Robust Q-learning","created":"2023-05-28","cited_by_count":29},{"id":"2302.05372","title":"Towards Minimax Optimality of Model-based Robust Reinforcement Learning","created":"2023-02-10","cited_by_count":22},{"id":"2006.00945","title":"Robust Reinforcement Learning with Wasserstein Constraint","created":"2020-06-01","cited_by_count":21},{"id":"2006.05630","title":"Distributionally Robust Batch Contextual Bandits","created":"2020-06-10","cited_by_count":20},{"id":"2305.10504","title":"Model-Free Robust Average-Reward Reinforcement Learning","created":"2023-05-17","cited_by_count":20},{"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":"2306.11626","title":"Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity","created":"2023-06-20","cited_by_count":17},{"id":"2403.12946","title":"Sample Complexity of Offline Distributionally Robust Linear Markov Decision Processes","created":"2024-03-19","cited_by_count":14},{"id":"2112.10935","title":"Nearly Optimal Policy Optimization with Stable at Any Time Guarantee","created":"2021-12-21","cited_by_count":13},{"id":"2307.08873","title":"An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient","created":"2023-07-17","cited_by_count":12},{"id":"2402.08991","title":"Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption","created":"2024-02-14","cited_by_count":12},{"id":"2302.01248","title":"Robust Markov Decision Processes without Model Estimation","created":"2023-02-02","cited_by_count":11},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11},{"id":"2210.15598","title":"Provable Sim-to-real Transfer in Continuous Domain with Partial Observations","created":"2022-10-27","cited_by_count":9},{"id":"2411.18612","title":"Robust Offline Reinforcement Learning with Linearly Structured f-Divergence Regularization","created":"2024-11-27","cited_by_count":8},{"id":"2505.18044","title":"Linear Mixture Distributionally Robust Markov Decision Processes","created":"2025-05-23","cited_by_count":5},{"id":"2312.04464","title":"Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation","created":"2023-12-07","cited_by_count":4},{"id":"2109.09470","title":"ACReL: Adversarial Conditional value-at-risk Reinforcement Learning","created":"2021-09-20","cited_by_count":2}],"next_cursor":null}