{"list":"other","total":56,"rows":[{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"1602.04589","title":"Optimal Best Arm Identification with Fixed Confidence","created":"2016-02-15","cited_by_count":239},{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213},{"id":"1503.02834","title":"Doubly Robust Policy Evaluation and Optimization","created":"2015-03-10","cited_by_count":158},{"id":"2211.07638","title":"Legged Locomotion in Challenging Terrains using Egocentric Vision","created":"2022-11-14","cited_by_count":151},{"id":"2003.02189","title":"Exploration-Exploitation in Constrained MDPs","created":"2020-03-04","cited_by_count":149},{"id":"2003.00534","title":"Provably Efficient Safe Exploration via Primal-Dual Policy Optimization","created":"2020-03-01","cited_by_count":134},{"id":"2110.04652","title":"Representation Learning for Online and Offline RL in Low-rank MDPs","created":"2021-10-09","cited_by_count":129},{"id":"2008.06626","title":"Safe Reinforcement Learning in Constrained Markov Decision Processes","created":"2020-08-15","cited_by_count":115},{"id":"1612.01205","title":"Optimal and Adaptive Off-policy Evaluation in Contextual Bandits","created":"2016-12-04","cited_by_count":111},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110},{"id":"1605.04812","title":"Off-policy evaluation for slate recommendation","created":"2016-05-16","cited_by_count":103},{"id":"2007.13442","title":"Fast active learning for pure exploration in reinforcement learning","created":"2020-07-27","cited_by_count":92},{"id":"1908.05814","title":"Linear Stochastic Bandits Under Safety Constraints","created":"2019-08-16","cited_by_count":90},{"id":"1907.09623","title":"Doubly robust off-policy evaluation with shrinkage","created":"2019-07-22","cited_by_count":87},{"id":"1811.03056","title":"Policy Certificates: Towards Accountable Reinforcement Learning","created":"2018-11-07","cited_by_count":81},{"id":"2010.01374","title":"Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions","created":"2020-10-03","cited_by_count":71},{"id":"2006.10185","title":"Stochastic Bandits with Linear Constraints","created":"2020-06-17","cited_by_count":68},{"id":"2401.10700","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","created":"2024-01-19","cited_by_count":64},{"id":"1802.06480","title":"Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning","created":"2018-02-19","cited_by_count":62},{"id":"1602.04282","title":"Conservative Bandits","created":"2016-02-13","cited_by_count":59},{"id":"1611.06426","title":"Conservative Contextual Linear Bandits","created":"2016-11-19","cited_by_count":57},{"id":"1910.13726","title":"Safe Exploration for Interactive Machine Learning","created":"2019-10-30","cited_by_count":51},{"id":"2003.00660","title":"Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss","created":"2020-03-02","cited_by_count":46},{"id":"2101.10895","title":"A Primal-Dual Approach to Constrained Markov Decision Processes","created":"2021-01-26","cited_by_count":42},{"id":"2108.02717","title":"Beyond No Regret: Instance-Dependent PAC Reinforcement Learning","created":"2021-08-05","cited_by_count":41},{"id":"1911.02156","title":"Safe Linear Thompson Sampling with Side Information","created":"2019-11-06","cited_by_count":37},{"id":"2206.06270","title":"Near-Optimal Sample Complexity Bounds for Constrained MDPs","created":"2022-06-13","cited_by_count":37},{"id":"2207.02575","title":"Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design","created":"2022-07-06","cited_by_count":33},{"id":"2212.09900","title":"Policy learning \"without\" overlap: Pessimism and generalized empirical Bernstein's inequality","created":"2022-12-19","cited_by_count":32},{"id":"2010.11002","title":"Optimal Off-Policy Evaluation from Multiple Logging Policies","created":"2020-10-21","cited_by_count":30},{"id":"2310.03225","title":"Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms","created":"2023-10-05","cited_by_count":28},{"id":"1706.03469","title":"Data-Efficient Policy Evaluation Through Behavior Policy Search","created":"2017-06-12","cited_by_count":26},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20},{"id":"2002.03221","title":"Improved Algorithms for Conservative Exploration in Bandits","created":"2020-02-08","cited_by_count":16},{"id":"2203.04510","title":"ReVar: Strengthening Policy Evaluation via Reduced Variance Sampling","created":"2022-03-09","cited_by_count":16},{"id":"2206.11183","title":"Active Learning with Safety Constraints","created":"2022-06-22","cited_by_count":16},{"id":"2111.14552","title":"Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning","created":"2021-11-29","cited_by_count":15},{"id":"2202.13234","title":"Safe Exploration for Efficient Policy Evaluation and Comparison","created":"2022-02-26","cited_by_count":15},{"id":"2305.17568","title":"Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities","created":"2023-05-27","cited_by_count":15},{"id":"2010.15963","title":"Deep Jump Learning for Off-Policy Evaluation in Continuous Treatment Settings","created":"2020-10-29","cited_by_count":14},{"id":"2012.08073","title":"Chernoff Sampling for Active Testing and Extension to Active Regression","created":"2020-12-15","cited_by_count":13},{"id":"2210.02087","title":"Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration and Planning","created":"2022-10-05","cited_by_count":12},{"id":"2302.06064","title":"Provably Safe Reinforcement Learning with Step-wise Violation Constraints","created":"2023-02-13","cited_by_count":11},{"id":"2106.11692","title":"A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning","created":"2021-06-22","cited_by_count":9},{"id":"2308.15006","title":"Directional Optimism for Safe Linear Bandits","created":"2023-08-29","cited_by_count":8},{"id":"1703.00579","title":"Active Learning for Accurate Estimation of Linear Models","created":"2017-03-02","cited_by_count":6},{"id":"2202.01721","title":"Variance-Optimal Augmentation Logging for Counterfactual Evaluation in Contextual Bandits","created":"2022-02-03","cited_by_count":6},{"id":"2310.09574","title":"Reduced Policy Optimization for Continuous Control with Hard Constraints","created":"2023-10-14","cited_by_count":6},{"id":"2207.06147","title":"A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP","created":"2022-07-13","cited_by_count":5},{"id":"2403.15928","title":"Safe Reinforcement Learning for Constrained Markov Decision Processes with Stochastic Stopping Time","created":"2024-03-23","cited_by_count":5},{"id":"2111.04835","title":"Safe Data Collection for Offline and Online Policy Learning","created":"2021-11-08","cited_by_count":4},{"id":"2301.12357","title":"SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits","created":"2023-01-29","cited_by_count":3}],"next_cursor":null}