{"list":"other","total":55,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"1905.00360","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","created":"2019-05-01","cited_by_count":287},{"id":"1604.00923","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","created":"2016-04-04","cited_by_count":286},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"1606.02647","title":"Safe and Efficient Off-Policy Reinforcement Learning","created":"2016-06-08","cited_by_count":264},{"id":"1906.04733","title":"DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections","created":"2019-06-10","cited_by_count":254},{"id":"1810.12429","title":"Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation","created":"2018-10-29","cited_by_count":227},{"id":"1901.00137","title":"A Theoretical Analysis of Deep Q-Learning","created":"2019-01-01","cited_by_count":215},{"id":"1912.02074","title":"AlgaeDICE: Policy Gradient from Arbitrary Experience","created":"2019-12-04","cited_by_count":188},{"id":"1912.05032","title":"Imitation Learning via Off-Policy Distribution Matching","created":"2019-12-10","cited_by_count":183},{"id":"1910.12809","title":"Minimax Weight and Q-Function Learning for Off-Policy Evaluation","created":"2019-10-28","cited_by_count":150},{"id":"1802.03493","title":"More Robust Doubly Robust Off-policy Evaluation","created":"2018-02-10","cited_by_count":141},{"id":"1802.04181","title":"State Representation Learning for Control: An Overview","created":"2018-02-12","cited_by_count":127},{"id":"1812.06110","title":"Dopamine: A Research Framework for Deep Reinforcement Learning","created":"2018-12-14","cited_by_count":122},{"id":"2002.09072","title":"GenDICE: Generalized Offline Estimation of Stationary Values","created":"2020-02-21","cited_by_count":122},{"id":"1911.06854","title":"Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning","created":"2019-11-15","cited_by_count":121},{"id":"1906.03393","title":"Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling","created":"2019-06-08","cited_by_count":119},{"id":"1807.11622","title":"Count-Based Exploration with the Successor Representation","created":"2018-07-31","cited_by_count":112},{"id":"1612.01205","title":"Optimal and Adaptive Off-policy Evaluation in Contextual Bandits","created":"2016-12-04","cited_by_count":111},{"id":"1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","created":"2019-10-03","cited_by_count":111},{"id":"1503.04269","title":"An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning","created":"2015-03-14","cited_by_count":103},{"id":"1605.04812","title":"Off-policy evaluation for slate recommendation","created":"2016-05-16","cited_by_count":103},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89},{"id":"1901.10964","title":"Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement","created":"2019-01-30","cited_by_count":88},{"id":"1710.11089","title":"Eigenoption Discovery through the Deep Successor Representation","created":"2017-10-30","cited_by_count":86},{"id":"2007.03438","title":"Off-Policy Evaluation via the Regularized Lagrangian","created":"2020-07-07","cited_by_count":86},{"id":"1606.02396","title":"Deep Successor Reinforcement Learning","created":"2016-06-08","cited_by_count":72},{"id":"2001.11113","title":"GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values","created":"2020-01-29","cited_by_count":70},{"id":"1702.07121","title":"Consistent On-Line Off-Policy Evaluation","created":"2017-02-23","cited_by_count":51},{"id":"1612.05533","title":"Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments","created":"2016-12-16","cited_by_count":50},{"id":"1811.00260","title":"Horizon: Facebook's Open Source Applied Reinforcement Learning Platform","created":"2018-11-01","cited_by_count":48},{"id":"1901.09455","title":"Off-Policy Deep Reinforcement Learning by Bootstrapping the Covariate Shift","created":"2019-01-27","cited_by_count":47},{"id":"1705.08080","title":"Visual Semantic Planning using Deep Successor Representations","created":"2017-05-23","cited_by_count":45},{"id":"2006.13169","title":"Experience Replay with Likelihood-free Importance Weights","created":"2020-06-23","cited_by_count":42},{"id":"2007.06049","title":"An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay","created":"2020-07-12","cited_by_count":41},{"id":"1910.06508","title":"Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling","created":"2019-10-15","cited_by_count":37},{"id":"1810.06530","title":"Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning","created":"2018-10-15","cited_by_count":35},{"id":"1811.09013","title":"An Off-policy Policy Gradient Theorem Using Emphatic Weightings","created":"2018-11-22","cited_by_count":34},{"id":"1905.01072","title":"Deep Residual Reinforcement Learning","created":"2019-05-03","cited_by_count":21},{"id":"1702.03006","title":"Multi-step Off-policy Learning Without Importance Sampling Ratios","created":"2017-02-09","cited_by_count":19},{"id":"1903.11329","title":"Generalized Off-Policy Actor-Critic","created":"2019-03-27","cited_by_count":16},{"id":"2003.04108","title":"Stable Policy Optimization via Off-Policy Divergence Regularization","created":"2020-03-09","cited_by_count":16},{"id":"2003.11126","title":"Black-box Off-policy Estimation for Infinite-Horizon Reinforcement Learning","created":"2020-03-24","cited_by_count":16},{"id":"1504.05539","title":"Temporal-Difference Networks","created":"2015-04-21","cited_by_count":13},{"id":"1911.10866","title":"Disentangled Cumulants Help Successor Representations Transfer to New Tasks","created":"2019-11-25","cited_by_count":11}],"next_cursor":null}