{"list":"other","total":54,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"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":"2302.12192","title":"Aligning Text-to-Image Models using Human Feedback","created":"2023-02-23","cited_by_count":422},{"id":"1610.09512","title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","created":"2016-10-29","cited_by_count":292},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"id":"2006.01107","title":"Model-Based Reinforcement Learning with Value-Targeted Regression","created":"2020-06-01","cited_by_count":234},{"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":"1912.05830","title":"Provably Efficient Exploration in Policy Optimization","created":"2019-12-12","cited_by_count":205},{"id":"1905.10389","title":"Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound","created":"2019-05-24","cited_by_count":201},{"id":"2012.08507","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes","created":"2020-12-15","cited_by_count":200},{"id":"2003.00153","title":"Learning Near Optimal Policies with Low Inherent Bellman Error","created":"2020-02-29","cited_by_count":181},{"id":"1802.09127","title":"Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling","created":"2018-02-26","cited_by_count":169},{"id":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"1402.0635","title":"Generalization and Exploration via Randomized Value Functions","created":"2014-02-04","cited_by_count":112},{"id":"1912.04136","title":"Optimism in Reinforcement Learning with Generalized Linear Function Approximation","created":"2019-12-09","cited_by_count":111},{"id":"2006.13165","title":"Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping","created":"2020-06-23","cited_by_count":102},{"id":"1911.00567","title":"Frequentist Regret Bounds for Randomized Least-Squares Value Iteration","created":"2019-11-01","cited_by_count":101},{"id":"2110.00871","title":"Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning","created":"2021-10-02","cited_by_count":66},{"id":"2203.05804","title":"Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism","created":"2022-03-11","cited_by_count":65},{"id":"2010.02966","title":"Reinforcement Learning with Random Delays","created":"2020-10-06","cited_by_count":59},{"id":"1906.02870","title":"Worst-Case Regret Bounds for Exploration via Randomized Value Functions","created":"2019-06-07","cited_by_count":57},{"id":"2212.06132","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes","created":"2022-12-12","cited_by_count":57},{"id":"1807.02089","title":"Linear Bandits with Stochastic Delayed Feedback","created":"2018-07-05","cited_by_count":55},{"id":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","cited_by_count":49},{"id":"1906.00670","title":"Nonstochastic Multiarmed Bandits with Unrestricted Delays","created":"2019-06-03","cited_by_count":46},{"id":"1910.06054","title":"An Optimal Algorithm for Adversarial Bandits with Arbitrary Delays","created":"2019-10-14","cited_by_count":44},{"id":"2006.10459","title":"Stochastic bandits with arm-dependent delays","created":"2020-06-18","cited_by_count":36},{"id":"2106.11960","title":"Variance-Aware Off-Policy Evaluation with Linear Function Approximation","created":"2021-06-22","cited_by_count":34},{"id":"2012.14843","title":"Learning Adversarial Markov Decision Processes with Delayed Feedback","created":"2020-12-29","cited_by_count":33},{"id":"2101.11992","title":"Acting in Delayed Environments with Non-Stationary Markov Policies","created":"2021-01-28","cited_by_count":31},{"id":"2106.11854","title":"Off-Policy Reinforcement Learning with Delayed Rewards","created":"2021-06-22","cited_by_count":25},{"id":"2207.10786","title":"Delayed Feedback in Generalised Linear Bandits Revisited","created":"2022-07-21","cited_by_count":23},{"id":"1811.01132","title":"VIREL: A Variational Inference Framework for Reinforcement Learning","created":"2018-11-03","cited_by_count":22},{"id":"2005.05441","title":"Delay-Aware Multi-Agent Reinforcement Learning for Cooperative and Competitive Environments","created":"2020-05-11","cited_by_count":22},{"id":"2201.13172","title":"Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback","created":"2022-01-31","cited_by_count":22},{"id":"2206.11254","title":"Langevin Monte Carlo for Contextual Bandits","created":"2022-06-22","cited_by_count":22},{"id":"2211.13208","title":"On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation","created":"2022-11-23","cited_by_count":22},{"id":"2012.09613","title":"Model-based Reinforcement Learning for Continuous Control with Posterior Sampling","created":"2020-11-20","cited_by_count":21},{"id":"2010.12163","title":"Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration","created":"2020-10-23","cited_by_count":19},{"id":"2011.07715","title":"Blind Decision Making: Reinforcement Learning with Delayed Observations","created":"2020-11-16","cited_by_count":15},{"id":"2006.06790","title":"On Frequentist Regret of Linear Thompson Sampling","created":"2020-06-11","cited_by_count":14},{"id":"2210.00750","title":"Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient","created":"2022-10-03","cited_by_count":12},{"id":"2002.10316","title":"Bandit Learning with Delayed Impact of Actions","created":"2020-02-24","cited_by_count":10},{"id":"2302.01477","title":"A Reduction-based Framework for Sequential Decision Making with Delayed Feedback","created":"2023-02-03","cited_by_count":7},{"id":"2111.07615","title":"Optimism and Delays in Episodic Reinforcement Learning","created":"2021-11-15","cited_by_count":5},{"id":"2306.08803","title":"Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning","created":"2023-06-15","cited_by_count":5},{"id":"2305.02527","title":"Reinforcement Learning with Delayed, Composite, and Partially Anonymous Reward","created":"2023-05-04","cited_by_count":2}],"next_cursor":null}