{"list":"other","total":57,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"id":"1505.00853","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","created":"2015-05-05","cited_by_count":519},{"id":"1807.03765","title":"Is Q-learning Provably Efficient?","created":"2018-07-10","cited_by_count":487},{"id":"1609.07152","title":"Input Convex Neural Networks","created":"2016-09-22","cited_by_count":414},{"id":"1610.09512","title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","created":"2016-10-29","cited_by_count":292},{"id":"1503.02101","title":"Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition","created":"2015-03-06","cited_by_count":243},{"id":"2006.01107","title":"Model-Based Reinforcement Learning with Value-Targeted Regression","created":"2020-06-01","cited_by_count":234},{"id":"2006.10814","title":"FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs","created":"2020-06-18","cited_by_count":233},{"id":"1912.05830","title":"Provably Efficient Exploration in Policy Optimization","created":"2019-12-12","cited_by_count":205},{"id":"1402.0555","title":"Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits","created":"2014-02-04","cited_by_count":201},{"id":"1905.10389","title":"Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound","created":"2019-05-24","cited_by_count":201},{"id":"1312.2139","title":"Optimal rates for zero-order convex optimization: the power of two function evaluations","created":"2013-12-07","cited_by_count":198},{"id":"2002.04926","title":"Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles","created":"2020-02-12","cited_by_count":197},{"id":"2003.00153","title":"Learning Near Optimal Policies with Low Inherent Bellman Error","created":"2020-02-29","cited_by_count":181},{"id":"1309.6869","title":"Finite-Time Analysis of Kernelised Contextual Bandits","created":"2013-09-26","cited_by_count":177},{"id":"1908.00261","title":"On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift","created":"2019-08-01","cited_by_count":177},{"id":"1901.09018","title":"Provably efficient RL with Rich Observations via Latent State Decoding","created":"2019-01-25","cited_by_count":169},{"id":"2006.06224","title":"A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning","created":"2020-06-11","cited_by_count":162},{"id":"1807.03858","title":"Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees","created":"2018-07-10","cited_by_count":140},{"id":"1704.00708","title":"No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis","created":"2017-04-03","cited_by_count":129},{"id":"1605.07272","title":"Matrix Completion has No Spurious Local Minimum","created":"2016-05-24","cited_by_count":125},{"id":"2002.07530","title":"Improved Optimistic Algorithms for Logistic Bandits","created":"2020-02-18","cited_by_count":118},{"id":"1406.1853","title":"Model-based Reinforcement Learning and the Eluder Dimension","created":"2014-06-07","cited_by_count":116},{"id":"2003.12699","title":"Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits under Realizability","created":"2020-03-28","cited_by_count":115},{"id":"1911.05815","title":"Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning","created":"2019-11-13","cited_by_count":114},{"id":"1912.04136","title":"Optimism in Reinforcement Learning with Generalized Linear Function Approximation","created":"2019-12-09","cited_by_count":111},{"id":"1910.10597","title":"Sample Complexity of Reinforcement Learning using Linearly Combined Model Ensembles","created":"2019-10-23","cited_by_count":100},{"id":"1803.01088","title":"Practical Contextual Bandits with Regression Oracles","created":"2018-03-03","cited_by_count":93},{"id":"2006.12466","title":"Information Theoretic Regret Bounds for Online Nonlinear Control","created":"2020-06-22","cited_by_count":90},{"id":"2010.03104","title":"Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective","created":"2020-10-07","cited_by_count":78},{"id":"1507.02030","title":"Beyond Convexity: Stochastic Quasi-Convex Optimization","created":"2015-07-08","cited_by_count":76},{"id":"1803.00606","title":"On Oracle-Efficient PAC RL with Rich Observations","created":"2018-03-01","cited_by_count":71},{"id":"2005.08068","title":"Model-Augmented Actor-Critic: Backpropagating through Paths","created":"2020-05-16","cited_by_count":63},{"id":"2011.04020","title":"High-Dimensional Sparse Linear Bandits","created":"2020-11-08","cited_by_count":61},{"id":"1711.03985","title":"Applications of Deep Learning and Reinforcement Learning to Biological Data","created":"2017-11-10","cited_by_count":45},{"id":"1910.06996","title":"Adaptive Exploration in Linear Contextual Bandit","created":"2019-10-15","cited_by_count":43},{"id":"2007.07876","title":"Upper Counterfactual Confidence Bounds: a New Optimism Principle for Contextual Bandits","created":"2020-07-15","cited_by_count":40},{"id":"1703.00048","title":"Provably Optimal Algorithms for Generalized Linear Contextual Bandits","created":"2017-02-28","cited_by_count":38},{"id":"2005.10804","title":"Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension","created":"2020-05-21","cited_by_count":37},{"id":"1805.11845","title":"An Information-Theoretic Analysis for Thompson Sampling with Many Actions","created":"2018-05-30","cited_by_count":35},{"id":"1905.04654","title":"On the Performance of Thompson Sampling on Logistic Bandits","created":"2019-05-12","cited_by_count":32},{"id":"1708.00075","title":"Efficient Regret Minimization in Non-Convex Games","created":"2017-07-31","cited_by_count":28},{"id":"1602.04915","title":"Gradient Descent Converges to Minimizers","created":"2016-02-16","cited_by_count":25},{"id":"2011.04018","title":"Online Sparse Reinforcement Learning","created":"2020-11-08","cited_by_count":25},{"id":"1706.05598","title":"On the Optimization Landscape of Tensor Decompositions","created":"2017-06-18","cited_by_count":21},{"id":"1912.06366","title":"Provably Efficient Reinforcement Learning with Aggregated States","created":"2019-12-13","cited_by_count":20},{"id":"2011.04622","title":"On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces","created":"2020-11-09","cited_by_count":19},{"id":"2007.06184","title":"Efficient Planning in Large MDPs with Weak Linear Function Approximation","created":"2020-07-13","cited_by_count":17},{"id":"2009.02003","title":"Nearly Dimension-Independent Sparse Linear Bandit over Small Action Spaces via Best Subset Selection","created":"2020-09-04","cited_by_count":12}],"next_cursor":null}