{"list":"other","total":65,"rows":[{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"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":"1707.02038","title":"A Tutorial on Thompson Sampling","created":"2017-07-07","cited_by_count":433},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1610.09512","title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","created":"2016-10-29","cited_by_count":292},{"id":"2006.01107","title":"Model-Based Reinforcement Learning with Value-Targeted Regression","created":"2020-06-01","cited_by_count":234},{"id":"1306.0940","title":"(More) Efficient Reinforcement Learning via Posterior Sampling","created":"2013-06-04","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":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"id":"1910.08348","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","created":"2019-10-18","cited_by_count":217},{"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":"1403.5341","title":"An Information-Theoretic Analysis of Thompson Sampling","created":"2014-03-21","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":"1901.09018","title":"Provably efficient RL with Rich Observations via Latent State Decoding","created":"2019-01-25","cited_by_count":169},{"id":"1403.5556","title":"Learning to Optimize via Information-Directed Sampling","created":"2014-03-21","cited_by_count":168},{"id":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120},{"id":"1607.00215","title":"Why is Posterior Sampling Better than Optimism for Reinforcement Learning?","created":"2016-07-01","cited_by_count":117},{"id":"1707.03497","title":"Value Prediction Network","created":"2017-07-11","cited_by_count":117},{"id":"1406.1853","title":"Model-based Reinforcement Learning and the Eluder Dimension","created":"2014-06-07","cited_by_count":116},{"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":"1510.08906","title":"Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning","created":"2015-10-29","cited_by_count":106},{"id":"2011.03506","title":"The Value Equivalence Principle for Model-Based Reinforcement Learning","created":"2020-11-06","cited_by_count":94},{"id":"1612.08810","title":"The Predictron: End-To-End Learning and Planning","created":"2016-12-28","cited_by_count":93},{"id":"1804.07193","title":"Lipschitz Continuity in Model-based Reinforcement Learning","created":"2018-04-19","cited_by_count":91},{"id":"1709.05380","title":"The Uncertainty Bellman Equation and Exploration","created":"2017-09-15","cited_by_count":82},{"id":"1803.00606","title":"On Oracle-Efficient PAC RL with Rich Observations","created":"2018-03-01","cited_by_count":71},{"id":"1701.04113","title":"Near Optimal Behavior via Approximate State Abstraction","created":"2017-01-15","cited_by_count":66},{"id":"1705.07347","title":"Ensemble Sampling","created":"2017-05-20","cited_by_count":62},{"id":"2008.02790","title":"Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices","created":"2020-08-06","cited_by_count":59},{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59},{"id":"1911.09724","title":"Information-Theoretic Confidence Bounds for Reinforcement Learning","created":"2019-11-21","cited_by_count":51},{"id":"2007.07170","title":"Goal-Aware Prediction: Learning to Model What Matters","created":"2020-07-14","cited_by_count":45},{"id":"1902.00470","title":"An Information-Theoretic Approach to Minimax Regret in Partial Monitoring","created":"2019-02-01","cited_by_count":42},{"id":"2009.12228","title":"Mirror Descent and the Information Ratio","created":"2020-09-25","cited_by_count":40},{"id":"1803.02855","title":"Satisficing in Time-Sensitive Bandit Learning","created":"2018-03-07","cited_by_count":39},{"id":"2006.07464","title":"Hypermodels for Exploration","created":"2020-06-12","cited_by_count":37},{"id":"1805.11845","title":"An Information-Theoretic Analysis for Thompson Sampling with Many Actions","created":"2018-05-30","cited_by_count":35},{"id":"1810.06530","title":"Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning","created":"2018-10-15","cited_by_count":35},{"id":"2106.03273","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","created":"2021-06-06","cited_by_count":35},{"id":"2106.10316","title":"Proper Value Equivalence","created":"2021-06-18","cited_by_count":33},{"id":"2204.01464","title":"Value Gradient weighted Model-Based Reinforcement Learning","created":"2022-04-04","cited_by_count":32},{"id":"2001.00805","title":"Making Sense of Reinforcement Learning and Probabilistic Inference","created":"2020-01-03","cited_by_count":30},{"id":"2203.00397","title":"A Theory of Abstraction in Reinforcement Learning","created":"2022-03-01","cited_by_count":27},{"id":"1905.11817","title":"Connections Between Mirror Descent, Thompson Sampling and the Information Ratio","created":"2019-05-28","cited_by_count":23},{"id":"2003.00030","title":"Policy-Aware Model Learning for Policy Gradient Methods","created":"2020-02-28","cited_by_count":23},{"id":"2101.06197","title":"Deciding What to Learn: A Rate-Distortion Approach","created":"2021-01-15","cited_by_count":23},{"id":"1301.1722","title":"Linear Bandits in High Dimension and Recommendation Systems","created":"2013-01-08","cited_by_count":22},{"id":"1301.6690","title":"Model-Based Bayesian Exploration","created":"2013-01-23","cited_by_count":21},{"id":"1912.06366","title":"Provably Efficient Reinforcement Learning with Aggregated States","created":"2019-12-13","cited_by_count":20},{"id":"1909.04115","title":"Gradient-Aware Model-based Policy Search","created":"2019-09-09","cited_by_count":19},{"id":"1902.00681","title":"First-Order Bayesian Regret Analysis of Thompson Sampling","created":"2019-02-02","cited_by_count":17},{"id":"2010.02255","title":"Temporal Difference Uncertainties as a Signal for Exploration","created":"2020-10-05","cited_by_count":15},{"id":"2110.13973","title":"The Value of Information When Deciding What to Learn","created":"2021-10-26","cited_by_count":15},{"id":"1406.3926","title":"Bayesian Optimal Control of Smoothly Parameterized Systems: The Lazy Posterior Sampling Algorithm","created":"2014-06-16","cited_by_count":11},{"id":"1612.02126","title":"Rate-cost tradeoffs in control","created":"2016-12-07","cited_by_count":9},{"id":"2006.13408","title":"Control-Aware Representations for Model-based Reinforcement Learning","created":"2020-06-24","cited_by_count":8},{"id":"1502.03762","title":"Rationally inattentive control of Markov processes","created":"2015-02-12","cited_by_count":6},{"id":"2010.02383","title":"Randomized Value Functions via Posterior State-Abstraction Sampling","created":"2020-10-05","cited_by_count":5},{"id":"1702.04126","title":"Gaussian-Dirichlet Posterior Dominance in Sequential Learning","created":"2017-02-14","cited_by_count":4},{"id":"1704.09028","title":"Time-Sensitive Bandit Learning and Satisficing Thompson Sampling","created":"2017-04-28","cited_by_count":3}],"next_cursor":null}