{"list":"other","total":57,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"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":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1603.00943","title":"CVXPY: A Python-Embedded Modeling Language for Convex Optimization","created":"2016-03-03","cited_by_count":641},{"id":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"2007.03964","title":"Responsive Safety in Reinforcement Learning by PID Lagrangian Methods","created":"2020-07-08","cited_by_count":316},{"id":"1805.07708","title":"A Lyapunov-based Approach to Safe Reinforcement Learning","created":"2018-05-20","cited_by_count":297},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"id":"1901.11275","title":"A Theory of Regularized Markov Decision Processes","created":"2019-01-31","cited_by_count":286},{"id":"1801.08757","title":"Safe Exploration in Continuous Action Spaces","created":"2018-01-26","cited_by_count":247},{"id":"1711.00141","title":"Training GANs with Optimism","created":"2017-10-31","cited_by_count":217},{"id":"1804.08617","title":"Distributed Distributional Deterministic Policy Gradients","created":"2018-04-23","cited_by_count":199},{"id":"1805.09801","title":"Meta-Gradient Reinforcement Learning","created":"2018-05-24","cited_by_count":159},{"id":"1910.13393","title":"Constrained Reinforcement Learning Has Zero Duality Gap","created":"2019-10-29","cited_by_count":151},{"id":"2003.02189","title":"Exploration-Exploitation in Constrained MDPs","created":"2020-03-04","cited_by_count":149},{"id":"1802.10551","title":"A Variational Inequality Perspective on Generative Adversarial Networks","created":"2018-02-28","cited_by_count":144},{"id":"1807.02629","title":"Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile","created":"2018-07-07","cited_by_count":136},{"id":"1908.03568","title":"Behaviour Suite for Reinforcement Learning","created":"2019-08-09","cited_by_count":132},{"id":"1802.05642","title":"The Mechanics of n-Player Differentiable Games","created":"2018-02-15","cited_by_count":118},{"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":"2005.09814","title":"Mirror Descent Policy Optimization","created":"2020-05-20","cited_by_count":106},{"id":"1807.03907","title":"The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization","created":"2018-07-11","cited_by_count":101},{"id":"1807.04252","title":"Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimization","created":"2018-07-11","cited_by_count":98},{"id":"1908.08465","title":"On the convergence of single-call stochastic extra-gradient methods","created":"2019-08-22","cited_by_count":89},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84},{"id":"2106.02684","title":"Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs","created":"2021-06-04","cited_by_count":80},{"id":"2010.14484","title":"One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL","created":"2020-10-27","cited_by_count":79},{"id":"2003.11881","title":"An empirical investigation of the challenges of real-world reinforcement learning","created":"2020-03-24","cited_by_count":77},{"id":"2206.05825","title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","created":"2022-06-12","cited_by_count":66},{"id":"2002.08456","title":"From Poincar\\'e Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization","created":"2020-02-19","cited_by_count":61},{"id":"2005.07513","title":"A Distributional View on Multi-Objective Policy Optimization","created":"2020-05-15","cited_by_count":52},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45},{"id":"2205.13521","title":"Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality","created":"2022-05-26","cited_by_count":37},{"id":"1808.04162","title":"A Forward-Backward Splitting Method for Monotone Inclusions Without Cocoercivity","created":"2018-08-13","cited_by_count":36},{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","cited_by_count":35},{"id":"1906.04349","title":"Learning to Score Behaviors for Guided Policy Optimization","created":"2019-06-11","cited_by_count":34},{"id":"2010.11151","title":"Logistic Q-Learning","created":"2020-10-21","cited_by_count":34},{"id":"2210.03096","title":"Accelerated Single-Call Methods for Constrained Min-Max Optimization","created":"2022-10-06","cited_by_count":32},{"id":"1807.09647","title":"Variational Bayesian Reinforcement Learning with Regret Bounds","created":"2018-07-25","cited_by_count":31},{"id":"2102.06924","title":"Online Apprenticeship Learning","created":"2021-02-13","cited_by_count":29},{"id":"2211.07357","title":"Controlling Commercial Cooling Systems Using Reinforcement Learning","created":"2022-11-11","cited_by_count":29},{"id":"1906.02027","title":"Last-iterate convergence rates for min-max optimization","created":"2019-06-05","cited_by_count":25},{"id":"2010.05380","title":"Efficient Wasserstein Natural Gradients for Reinforcement Learning","created":"2020-10-12","cited_by_count":23},{"id":"2106.00669","title":"Discovering Diverse Nearly Optimal Policies with Successor Features","created":"2021-06-01","cited_by_count":20},{"id":"2010.06324","title":"Balancing Constraints and Rewards with Meta-Gradient D4PG","created":"2020-10-13","cited_by_count":18},{"id":"1911.01679","title":"Apprenticeship Learning via Frank-Wolfe","created":"2019-11-05","cited_by_count":13},{"id":"2111.02994","title":"Towards an Understanding of Default Policies in Multitask Policy Optimization","created":"2021-11-04","cited_by_count":8},{"id":"2010.15268","title":"Understanding the Pathologies of Approximate Policy Evaluation when Combined with Greedification in Reinforcement Learning","created":"2020-10-28","cited_by_count":7},{"id":"2110.15688","title":"Variational Bayesian Optimistic Sampling","created":"2021-10-29","cited_by_count":7},{"id":"1708.05448","title":"On Ensuring that Intelligent Machines Are Well-Behaved","created":"2017-08-17","cited_by_count":3},{"id":"2301.03236","title":"Optimistic Meta-Gradients","created":"2023-01-09","cited_by_count":2}],"next_cursor":null}