{"list":"other","total":53,"rows":[{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"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":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"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":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"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":"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":"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":"1512.08562","title":"Taming the Noise in Reinforcement Learning via Soft Updates","created":"2015-12-28","cited_by_count":127},{"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":"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":"1711.04203","title":"Building machines that adapt and compute like brains","created":"2017-11-11","cited_by_count":99},{"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":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59},{"id":"1905.01240","title":"Information asymmetry in KL-regularized RL","created":"2019-05-03","cited_by_count":53},{"id":"1911.09724","title":"Information-Theoretic Confidence Bounds for Reinforcement Learning","created":"2019-11-21","cited_by_count":51},{"id":"2105.06948","title":"People construct simplified mental representations to plan","created":"2021-05-14","cited_by_count":47},{"id":"2007.07170","title":"Goal-Aware Prediction: Learning to Model What Matters","created":"2020-07-14","cited_by_count":45},{"id":"2102.05261","title":"Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States","created":"2021-02-10","cited_by_count":43},{"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":"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":"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":"2103.06224","title":"An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning","created":"2021-03-10","cited_by_count":20},{"id":"1909.04115","title":"Gradient-Aware Model-based Policy Search","created":"2019-09-09","cited_by_count":19},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19},{"id":"1905.05176","title":"Towards a Quantum-Like Cognitive Architecture for Decision-Making","created":"2019-05-11","cited_by_count":17},{"id":"1903.07438","title":"Exploiting Hierarchy for Learning and Transfer in KL-regularized RL","created":"2019-03-18","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":"1703.01585","title":"A Unified Bellman Equation for Causal Information and Value in Markov Decision Processes","created":"2017-03-05","cited_by_count":11},{"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":"2002.05769","title":"The Efficiency of Human Cognition Reflects Planned Information Processing","created":"2020-02-13","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":"1704.09028","title":"Time-Sensitive Bandit Learning and Satisficing Thompson Sampling","created":"2017-04-28","cited_by_count":3},{"id":"2206.02025","title":"Between Rate-Distortion Theory & Value Equivalence in Model-Based Reinforcement Learning","created":"2022-06-04","cited_by_count":2}],"next_cursor":null}