{"list":"other","total":70,"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":"1707.02038","title":"A Tutorial on Thompson Sampling","created":"2017-07-07","cited_by_count":433},{"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":"2112.13487","title":"The Statistical Complexity of Interactive Decision Making","created":"2021-12-27","cited_by_count":218},{"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":"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":"1901.10902","title":"InfoBot: Transfer and Exploration via the Information Bottleneck","created":"2019-01-30","cited_by_count":78},{"id":"1402.6028","title":"Algorithms for multi-armed bandit problems","created":"2014-02-25","cited_by_count":64},{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59},{"id":"1309.6821","title":"Sample Complexity of Multi-task Reinforcement Learning","created":"2013-09-26","cited_by_count":58},{"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":"1512.04860","title":"Increasing the Action Gap: New Operators for Reinforcement Learning","created":"2015-12-15","cited_by_count":49},{"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":"1311.0466","title":"Thompson Sampling for Complex Bandit Problems","created":"2013-11-03","cited_by_count":43},{"id":"2102.05261","title":"Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States","created":"2021-02-10","cited_by_count":43},{"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":"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":"1906.10667","title":"Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives","created":"2019-06-25","cited_by_count":30},{"id":"2001.00805","title":"Making Sense of Reinforcement Learning and Probabilistic Inference","created":"2020-01-03","cited_by_count":30},{"id":"2110.01593","title":"Generalized Kernel Thinning","created":"2021-10-04","cited_by_count":29},{"id":"1304.5758","title":"Prior-free and prior-dependent regret bounds for Thompson Sampling","created":"2013-04-21","cited_by_count":25},{"id":"2206.04640","title":"Regret Bounds for Information-Directed Reinforcement Learning","created":"2022-06-09","cited_by_count":24},{"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":"2109.00127","title":"Cognitive science as a source of forward and inverse models of human decisions for robotics and control","created":"2021-09-01","cited_by_count":22},{"id":"1909.04115","title":"Gradient-Aware Model-based Policy Search","created":"2019-09-09","cited_by_count":19},{"id":"2005.06641","title":"A Rate-Distortion view of human pragmatic reasoning","created":"2020-05-13","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":"1802.01282","title":"Coordinated Exploration in Concurrent Reinforcement Learning","created":"2018-02-05","cited_by_count":17},{"id":"1905.05176","title":"Towards a Quantum-Like Cognitive Architecture for Decision-Making","created":"2019-05-11","cited_by_count":17},{"id":"2205.10895","title":"Contextual Information-Directed Sampling","created":"2022-05-22","cited_by_count":16},{"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":"2004.11935","title":"The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget","created":"2020-04-24","cited_by_count":13},{"id":"2201.11817","title":"Modeling Human Exploration Through Resource-Rational Reinforcement Learning","created":"2022-01-27","cited_by_count":13},{"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":"1805.08948","title":"Scalable Coordinated Exploration in Concurrent Reinforcement Learning","created":"2018-05-23","cited_by_count":10},{"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":"1904.03964","title":"Bounded rational decision-making from elementary computations that reduce uncertainty","created":"2019-04-08","cited_by_count":4}],"next_cursor":null}