{"list":"other","total":63,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"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":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1909.05207","title":"Introduction to Online Convex Optimization","created":"2019-09-07","cited_by_count":803},{"id":"1405.4980","title":"Convex Optimization: Algorithms and Complexity","created":"2014-05-20","cited_by_count":575},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"2005.06392","title":"On the Global Convergence Rates of Softmax Policy Gradient Methods","created":"2020-05-13","cited_by_count":264},{"id":"1311.1869","title":"Optimization, Learning, and Games with Predictable Sequences","created":"2013-11-08","cited_by_count":188},{"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":"2007.06558","title":"Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization","created":"2020-07-13","cited_by_count":176},{"id":"1805.09801","title":"Meta-Gradient Reinforcement Learning","created":"2018-05-24","cited_by_count":159},{"id":"2102.00135","title":"Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes","created":"2021-01-30","cited_by_count":156},{"id":"1906.01786","title":"Global Optimality Guarantees For Policy Gradient Methods","created":"2019-06-05","cited_by_count":150},{"id":"1802.07245","title":"Meta-Reinforcement Learning of Structured Exploration Strategies","created":"2018-02-20","cited_by_count":130},{"id":"2201.07443","title":"On the Convergence Rates of Policy Gradient Methods","created":"2022-01-19","cited_by_count":119},{"id":"1909.02769","title":"Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs","created":"2019-09-06","cited_by_count":118},{"id":"1610.05708","title":"Relatively-Smooth Convex Optimization by First-Order Methods, and Applications","created":"2016-10-18","cited_by_count":108},{"id":"2005.09814","title":"Mirror Descent Policy Optimization","created":"2020-05-20","cited_by_count":106},{"id":"1804.06459","title":"On Learning Intrinsic Rewards for Policy Gradient Methods","created":"2018-04-17","cited_by_count":102},{"id":"1802.04821","title":"Evolved Policy Gradients","created":"2018-02-13","cited_by_count":88},{"id":"1910.04098","title":"Improving Generalization in Meta Reinforcement Learning using Learned Objectives","created":"2019-10-09","cited_by_count":68},{"id":"2007.12509","title":"Monte-Carlo Tree Search as Regularized Policy Optimization","created":"2020-07-24","cited_by_count":61},{"id":"1906.05374","title":"Meta-Learning via Learned Loss","created":"2019-06-12","cited_by_count":60},{"id":"1310.7780","title":"The Information Geometry of Mirror Descent","created":"2013-10-29","cited_by_count":54},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53},{"id":"2007.08433","title":"Meta-Gradient Reinforcement Learning with an Objective Discovered Online","created":"2020-07-16","cited_by_count":52},{"id":"2007.11120","title":"On Linear Convergence of Policy Gradient Methods for Finite MDPs","created":"2020-07-21","cited_by_count":52},{"id":"2105.01424","title":"On the Linear convergence of Natural Policy Gradient Algorithm","created":"2021-05-04","cited_by_count":48},{"id":"2210.01400","title":"Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies","created":"2022-10-04","cited_by_count":46},{"id":"1909.04607","title":"Discovery of Useful Questions as Auxiliary Tasks","created":"2019-09-10","cited_by_count":45},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45},{"id":"2105.06072","title":"Leveraging Non-uniformity in First-order Non-convex Optimization","created":"2021-05-13","cited_by_count":44},{"id":"2005.08158","title":"Optimizing for the Future in Non-Stationary MDPs","created":"2020-05-17","cited_by_count":37},{"id":"2003.14089","title":"Leverage the Average: an Analysis of KL Regularization in RL","created":"2020-03-31","cited_by_count":33},{"id":"1706.09529","title":"Learning to Learn: Meta-Critic Networks for Sample Efficient Learning","created":"2017-06-29","cited_by_count":28},{"id":"2104.13844","title":"A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning","created":"2021-04-28","cited_by_count":26},{"id":"2301.06276","title":"The Role of Baselines in Policy Gradient Optimization","created":"2023-01-16","cited_by_count":25},{"id":"1807.10455","title":"Acceleration through Optimistic No-Regret Dynamics","created":"2018-07-27","cited_by_count":22},{"id":"1306.0386","title":"Improved and Generalized Upper Bounds on the Complexity of Policy Iteration","created":"2013-06-03","cited_by_count":21},{"id":"2111.11309","title":"No-Regret Dynamics in the Fenchel Game: A Unified Framework for Algorithmic Convex Optimization","created":"2021-11-22","cited_by_count":20},{"id":"2302.01275","title":"ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs","created":"2023-02-02","cited_by_count":20},{"id":"1910.09322","title":"Momentum in Reinforcement Learning","created":"2019-10-21","cited_by_count":19},{"id":"2102.12611","title":"Improved Regret Bound and Experience Replay in Regularized Policy Iteration","created":"2021-02-25","cited_by_count":18},{"id":"2110.15572","title":"Understanding the Effect of Stochasticity in Policy Optimization","created":"2021-10-29","cited_by_count":18},{"id":"1905.09963","title":"A First-Order Approach To Accelerated Value Iteration","created":"2019-05-23","cited_by_count":17},{"id":"2209.15382","title":"Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization","created":"2022-09-30","cited_by_count":17},{"id":"1809.09501","title":"Anderson Acceleration for Reinforcement Learning","created":"2018-09-25","cited_by_count":15},{"id":"2209.06159","title":"Meta-Gradients in Non-Stationary Environments","created":"2022-09-13","cited_by_count":11},{"id":"2107.01715","title":"Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction","created":"2021-07-04","cited_by_count":10},{"id":"1810.06509","title":"Predictor-Corrector Policy Optimization","created":"2018-10-15","cited_by_count":9},{"id":"2002.03069","title":"Adaptive Approximate Policy Iteration","created":"2020-02-08","cited_by_count":9},{"id":"2201.12403","title":"Planning and Learning with Adaptive Lookahead","created":"2022-01-28","cited_by_count":8},{"id":"1805.07956","title":"Multiple-Step Greedy Policies in Online and Approximate Reinforcement Learning","created":"2018-05-21","cited_by_count":7},{"id":"1905.11591","title":"Beyond Exponentially Discounted Sum: Automatic Learning of Return Function","created":"2019-05-28","cited_by_count":7},{"id":"2006.16840","title":"Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization","created":"2020-06-30","cited_by_count":7},{"id":"1509.05760","title":"Accelerating Optimization via Adaptive Prediction","created":"2015-09-18","cited_by_count":5},{"id":"2112.02045","title":"An Analytical Update Rule for General Policy Optimization","created":"2021-12-03","cited_by_count":3},{"id":"2301.13236","title":"Policy Gradient with Tree Expansion","created":"2023-01-30","cited_by_count":3},{"id":"2301.03236","title":"Optimistic Meta-Gradients","created":"2023-01-09","cited_by_count":2}],"next_cursor":null}