{"list":"other","total":69,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"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":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"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":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"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":"1610.09512","title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","created":"2016-10-29","cited_by_count":292},{"id":"1812.02690","title":"Provably Efficient Maximum Entropy Exploration","created":"2018-12-06","cited_by_count":242},{"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":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223},{"id":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"id":"2112.13487","title":"The Statistical Complexity of Interactive Decision Making","created":"2021-12-27","cited_by_count":218},{"id":"1810.08678","title":"Optimization of Molecules via Deep Reinforcement Learning","created":"2018-10-19","cited_by_count":200},{"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":"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":"1907.02057","title":"Benchmarking Model-Based Reinforcement Learning","created":"2019-07-03","cited_by_count":162},{"id":"1711.10907","title":"Deep Reinforcement Learning for De-Novo Drug Design","created":"2017-11-29","cited_by_count":161},{"id":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"1509.08731","title":"Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning","created":"2015-09-29","cited_by_count":144},{"id":"1512.08562","title":"Taming the Noise in Reinforcement Learning via Soft Updates","created":"2015-12-28","cited_by_count":127},{"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":"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":"2007.08459","title":"PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning","created":"2020-07-16","cited_by_count":92},{"id":"1709.05380","title":"The Uncertainty Bellman Equation and Exploration","created":"2017-09-15","cited_by_count":82},{"id":"1901.10902","title":"InfoBot: Transfer and Exploration via the Information Bottleneck","created":"2019-01-30","cited_by_count":78},{"id":"1803.00606","title":"On Oracle-Efficient PAC RL with Rich Observations","created":"2018-03-01","cited_by_count":71},{"id":"1805.07563","title":"Reinforcement Learning of Theorem Proving","created":"2018-05-19","cited_by_count":69},{"id":"1701.04113","title":"Near Optimal Behavior via Approximate State Abstraction","created":"2017-01-15","cited_by_count":66},{"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":"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":"2206.07659","title":"Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity","created":"2022-06-15","cited_by_count":32},{"id":"2208.10904","title":"A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning","created":"2022-08-23","cited_by_count":31},{"id":"2302.09205","title":"Approximate Thompson Sampling via Epistemic Neural Networks","created":"2023-02-18","cited_by_count":31},{"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":"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":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19},{"id":"2206.03633","title":"Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping","created":"2022-06-08","cited_by_count":19},{"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":"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":"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":"2210.16877","title":"On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning","created":"2022-10-30","cited_by_count":6},{"id":"2210.16872","title":"Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction","created":"2022-10-30","cited_by_count":4},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","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}