{"list":"other","total":56,"rows":[{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"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":"1801.05039","title":"Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator","created":"2018-01-15","cited_by_count":250},{"id":"1306.0940","title":"(More) Efficient Reinforcement Learning via Posterior Sampling","created":"2013-06-04","cited_by_count":233},{"id":"1903.08568","title":"Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices","created":"2019-03-20","cited_by_count":227},{"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":"2112.13487","title":"The Statistical Complexity of Interactive Decision Making","created":"2021-12-27","cited_by_count":218},{"id":"1905.10389","title":"Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound","created":"2019-05-24","cited_by_count":201},{"id":"2103.10897","title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL","created":"2021-03-19","cited_by_count":178},{"id":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"1806.09460","title":"A Tour of Reinforcement Learning: The View from Continuous Control","created":"2018-06-25","cited_by_count":151},{"id":"1610.01283","title":"EPOpt: Learning Robust Neural Network Policies Using Model Ensembles","created":"2016-10-05","cited_by_count":138},{"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":"2001.09576","title":"Naive Exploration is Optimal for Online LQR","created":"2020-01-27","cited_by_count":116},{"id":"1402.0635","title":"Generalization and Exploration via Randomized Value Functions","created":"2014-02-04","cited_by_count":112},{"id":"1910.10597","title":"Sample Complexity of Reinforcement Learning using Linearly Combined Model Ensembles","created":"2019-10-23","cited_by_count":100},{"id":"1902.08721","title":"Online Control with Adversarial Disturbances","created":"2019-02-23","cited_by_count":92},{"id":"2006.12466","title":"Information Theoretic Regret Bounds for Online Nonlinear Control","created":"2020-06-22","cited_by_count":90},{"id":"1805.09388","title":"Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator","created":"2018-05-23","cited_by_count":86},{"id":"2001.09254","title":"Improper Learning for Non-Stochastic Control","created":"2020-01-25","cited_by_count":83},{"id":"1902.06223","title":"Learning Linear-Quadratic Regulators Efficiently with only $\\sqrt{T}$ Regret","created":"2019-02-17","cited_by_count":70},{"id":"1709.04570","title":"Learning Unknown Markov Decision Processes: A Thompson Sampling Approach","created":"2017-09-14","cited_by_count":65},{"id":"1806.07104","title":"Online Linear Quadratic Control","created":"2018-06-19","cited_by_count":56},{"id":"2103.12923","title":"Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation","created":"2021-03-24","cited_by_count":53},{"id":"2209.05423","title":"Statistical Learning Theory for Control: A Finite Sample Perspective","created":"2022-09-12","cited_by_count":53},{"id":"1911.12178","title":"The Nonstochastic Control Problem","created":"2019-11-27","cited_by_count":52},{"id":"1507.02592","title":"Fast rates in statistical and online learning","created":"2015-07-09","cited_by_count":47},{"id":"2007.06650","title":"Black-Box Control for Linear Dynamical Systems","created":"2020-07-13","cited_by_count":43},{"id":"1810.06530","title":"Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning","created":"2018-10-15","cited_by_count":35},{"id":"1809.01382","title":"On the optimality of the Hedge algorithm in the stochastic regime","created":"2018-09-05","cited_by_count":33},{"id":"2102.03758","title":"Non-stationary Online Learning with Memory and Non-stochastic Control","created":"2021-02-07","cited_by_count":33},{"id":"2312.16730","title":"Foundations of Reinforcement Learning and Interactive Decision Making","created":"2023-12-27","cited_by_count":33},{"id":"2301.08215","title":"Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient","created":"2023-01-19","cited_by_count":30},{"id":"2011.04018","title":"Online Sparse Reinforcement Learning","created":"2020-11-08","cited_by_count":25},{"id":"2011.13101","title":"Regret Bounds for Adaptive Nonlinear Control","created":"2020-11-26","cited_by_count":25},{"id":"2012.09613","title":"Model-based Reinforcement Learning for Continuous Control with Posterior Sampling","created":"2020-11-20","cited_by_count":21},{"id":"2010.04891","title":"Online Optimal Control with Affine Constraints","created":"2020-10-10","cited_by_count":20},{"id":"2007.06482","title":"Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation","created":"2020-07-13","cited_by_count":18},{"id":"2305.00477","title":"Posterior Sampling for Deep Reinforcement Learning","created":"2023-04-30","cited_by_count":16},{"id":"1703.08972","title":"Thompson Sampling for Linear-Quadratic Control Problems","created":"2017-03-27","cited_by_count":14},{"id":"2210.12320","title":"Online Adaptive Policy Selection in Time-Varying Systems: No-Regret via Contractive Perturbations","created":"2022-10-22","cited_by_count":14},{"id":"2006.12620","title":"A maximum-entropy approach to off-policy evaluation in average-reward MDPs","created":"2020-06-17","cited_by_count":9},{"id":"2301.08445","title":"Online switching control with stability and regret guarantees","created":"2023-01-20","cited_by_count":9},{"id":"2206.08520","title":"Thompson Sampling Achieves $\\tilde O(\\sqrt{T})$ Regret in Linear Quadratic Control","created":"2022-06-17","cited_by_count":8},{"id":"2404.05318","title":"Stochastic Online Optimization for Cyber-Physical and Robotic Systems","created":"2024-04-08","cited_by_count":6},{"id":"2211.15931","title":"Posterior Sampling for Continuing Environments","created":"2022-11-29","cited_by_count":4},{"id":"2304.12886","title":"What can online reinforcement learning with function approximation benefit from general coverage conditions?","created":"2023-04-25","cited_by_count":4},{"id":"2409.11141","title":"Sample Complexity Bounds for Linear System Identification from a Finite Set","created":"2024-09-17","cited_by_count":3},{"id":"2304.03321","title":"Adaptive Decision-Making with Constraints and Dependent Losses: Performance Guarantees and Applications to Online and Nonlinear Identification","created":"2023-04-06","cited_by_count":2},{"id":"2309.02815","title":"Near-continuous time Reinforcement Learning for continuous state-action spaces","created":"2023-09-06","cited_by_count":2},{"id":"2410.03230","title":"Online Bandit Nonlinear Control with Dynamic Batch Length and Adaptive Learning Rate","created":"2024-10-04","cited_by_count":2},{"id":"2312.05607","title":"Closed-Loop Finite-Time Analysis of Suboptimal Online Control","created":"2023-12-09","cited_by_count":1}],"next_cursor":null}