{"list":"other","total":52,"rows":[{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"id":"1604.00923","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","created":"2016-04-04","cited_by_count":286},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1606.02647","title":"Safe and Efficient Off-Policy Reinforcement Learning","created":"2016-06-08","cited_by_count":264},{"id":"1906.04733","title":"DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections","created":"2019-06-10","cited_by_count":254},{"id":"1810.12429","title":"Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation","created":"2018-10-29","cited_by_count":227},{"id":"1709.04326","title":"Learning with Opponent-Learning Awareness","created":"2017-09-13","cited_by_count":222},{"id":"1910.12809","title":"Minimax Weight and Q-Function Learning for Off-Policy Evaluation","created":"2019-10-28","cited_by_count":150},{"id":"1906.03393","title":"Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling","created":"2019-06-08","cited_by_count":119},{"id":"2001.01866","title":"Reinforcement Learning via Fenchel-Rockafellar Duality","created":"2020-01-07","cited_by_count":100},{"id":"2009.06799","title":"The Importance of Pessimism in Fixed-Dataset Policy Optimization","created":"2020-09-15","cited_by_count":99},{"id":"2011.06619","title":"Learning Latent Representations to Influence Multi-Agent Interaction","created":"2020-11-12","cited_by_count":93},{"id":"2007.08459","title":"PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning","created":"2020-07-16","cited_by_count":92},{"id":"1905.12495","title":"Deep Generalized Method of Moments for Instrumental Variable Analysis","created":"2019-05-29","cited_by_count":88},{"id":"1909.09146","title":"Weighted Linear Bandits for Non-Stationary Environments","created":"2019-09-19","cited_by_count":86},{"id":"2007.03438","title":"Off-Policy Evaluation via the Regularized Lagrangian","created":"2020-07-07","cited_by_count":86},{"id":"1910.05512","title":"Influence-Based Multi-Agent Exploration","created":"2019-10-12","cited_by_count":75},{"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":"1909.03739","title":"Off-Policy Evaluation in Partially Observable Environments","created":"2019-09-09","cited_by_count":66},{"id":"2010.07154","title":"Learning Deep Features in Instrumental Variable Regression","created":"2020-10-14","cited_by_count":66},{"id":"2010.11652","title":"CoinDICE: Off-Policy Confidence Interval Estimation","created":"2020-10-22","cited_by_count":64},{"id":"2005.10619","title":"A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments","created":"2020-05-19","cited_by_count":62},{"id":"2003.05623","title":"Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding","created":"2020-03-12","cited_by_count":61},{"id":"1702.07274","title":"Rotting Bandits","created":"2017-02-23","cited_by_count":57},{"id":"1602.04951","title":"Q($\\lambda$) with Off-Policy Corrections","created":"2016-02-16","cited_by_count":48},{"id":"2006.10701","title":"Deep Reinforcement Learning amidst Lifelong Non-Stationarity","created":"2020-06-18","cited_by_count":43},{"id":"2104.12820","title":"Universal Off-Policy Evaluation","created":"2021-04-26","cited_by_count":43},{"id":"2007.13893","title":"Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders","created":"2020-07-27","cited_by_count":41},{"id":"2005.08158","title":"Optimizing for the Future in Non-Stationary MDPs","created":"2020-05-17","cited_by_count":37},{"id":"2109.11052","title":"On Bonus-Based Exploration Methods in the Arcade Learning Environment","created":"2021-09-22","cited_by_count":37},{"id":"2010.12645","title":"Towards Safe Policy Improvement for Non-Stationary MDPs","created":"2020-10-23","cited_by_count":26},{"id":"2110.08229","title":"Influencing Towards Stable Multi-Agent Interactions","created":"2021-10-05","cited_by_count":24},{"id":"2010.04244","title":"Nonstationary Reinforcement Learning with Linear Function Approximation","created":"2020-10-08","cited_by_count":23},{"id":"1803.01731","title":"Me, My Echo Chamber, and I: Introspection on Social Media Polarization","created":"2018-03-05","cited_by_count":20},{"id":"1301.3892","title":"Nash Convergence of Gradient Dynamics in Iterated General-Sum Games","created":"2013-01-16","cited_by_count":18},{"id":"2105.09452","title":"Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection","created":"2021-05-20","cited_by_count":18},{"id":"1507.01569","title":"Emphatic Temporal-Difference Learning","created":"2015-07-06","cited_by_count":16},{"id":"1505.05798","title":"Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret","created":"2015-05-21","cited_by_count":15},{"id":"2004.14954","title":"On Deep Instrumental Variables Estimate","created":"2020-04-30","cited_by_count":14},{"id":"1906.00190","title":"Neural Replicator Dynamics","created":"2019-06-01","cited_by_count":13},{"id":"2002.02081","title":"Minimax Value Interval for Off-Policy Evaluation and Policy Optimization","created":"2020-02-06","cited_by_count":11},{"id":"2103.05741","title":"Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual Bounds","created":"2021-03-09","cited_by_count":11},{"id":"1905.03970","title":"Reinforcement Learning in Non-Stationary Environments","created":"2019-05-10","cited_by_count":10},{"id":"2009.07346","title":"Reinforcement Learning for Strategic Recommendations","created":"2020-09-15","cited_by_count":8},{"id":"2105.08834","title":"Meta-Reinforcement Learning by Tracking Task Non-stationarity","created":"2021-05-18","cited_by_count":8},{"id":"1905.12370","title":"Cascading Non-Stationary Bandits: Online Learning to Rank in the Non-Stationary Cascade Model","created":"2019-05-29","cited_by_count":5},{"id":"2111.03936","title":"SOPE: Spectrum of Off-Policy Estimators","created":"2021-11-06","cited_by_count":5},{"id":"2112.06625","title":"Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization","created":"2021-12-13","cited_by_count":5},{"id":"1710.07328","title":"Online Monotone Games","created":"2017-10-19","cited_by_count":3},{"id":"1909.05886","title":"Nearly Optimal Algorithms for Piecewise-Stationary Cascading Bandits","created":"2019-09-12","cited_by_count":2}],"next_cursor":null}