{"list":"other","total":54,"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":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"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":"1912.02762","title":"Normalizing Flows for Probabilistic Modeling and Inference","created":"2019-12-05","cited_by_count":1323},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"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":"1611.01224","title":"Sample Efficient Actor-Critic with Experience Replay","created":"2016-11-03","cited_by_count":188},{"id":"1908.09453","title":"OpenSpiel: A Framework for Reinforcement Learning in Games","created":"2019-08-26","cited_by_count":186},{"id":"1507.08750","title":"Action-Conditional Video Prediction using Deep Networks in Atari Games","created":"2015-07-31","cited_by_count":172},{"id":"1602.02867","title":"Value Iteration Networks","created":"2016-02-09","cited_by_count":160},{"id":"1805.09801","title":"Meta-Gradient Reinforcement Learning","created":"2018-05-24","cited_by_count":159},{"id":"1707.06203","title":"Imagination-Augmented Agents for Deep Reinforcement Learning","created":"2017-07-19","cited_by_count":140},{"id":"2009.04416","title":"Phasic Policy Gradient","created":"2020-09-09","cited_by_count":123},{"id":"1906.05243","title":"When to use parametric models in reinforcement learning?","created":"2019-06-12","cited_by_count":118},{"id":"1707.03497","title":"Value Prediction Network","created":"2017-07-11","cited_by_count":117},{"id":"2005.09814","title":"Mirror Descent Policy Optimization","created":"2020-05-20","cited_by_count":106},{"id":"2004.14646","title":"Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning","created":"2020-04-30","cited_by_count":102},{"id":"2011.03506","title":"The Value Equivalence Principle for Model-Based Reinforcement Learning","created":"2020-11-06","cited_by_count":94},{"id":"1612.08810","title":"The Predictron: End-To-End Learning and Planning","created":"2016-12-28","cited_by_count":93},{"id":"1602.07714","title":"Learning values across many orders of magnitude","created":"2016-02-24","cited_by_count":85},{"id":"1901.03559","title":"An investigation of model-free planning","created":"2019-01-11","cited_by_count":66},{"id":"1906.09237","title":"Shaping Belief States with Generative Environment Models for RL","created":"2019-06-21","cited_by_count":66},{"id":"2011.04021","title":"On the role of planning in model-based deep reinforcement learning","created":"2020-11-08","cited_by_count":57},{"id":"1805.11593","title":"Observe and Look Further: Achieving Consistent Performance on Atari","created":"2018-05-29","cited_by_count":44},{"id":"1811.06407","title":"Neural Predictive Belief Representations","created":"2018-11-15","cited_by_count":40},{"id":"1909.11583","title":"Off-Policy Actor-Critic with Shared Experience Replay","created":"2019-09-25","cited_by_count":39},{"id":"2006.16712","title":"Model-based Reinforcement Learning: A Survey","created":"2020-06-30","cited_by_count":39},{"id":"2003.14089","title":"Leverage the Average: an Analysis of KL Regularization in RL","created":"2020-03-31","cited_by_count":33},{"id":"1910.04142","title":"Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models","created":"2019-10-09","cited_by_count":26},{"id":"1907.02908","title":"On Inductive Biases in Deep Reinforcement Learning","created":"2019-07-05","cited_by_count":24},{"id":"2002.02836","title":"Causally Correct Partial Models for Reinforcement Learning","created":"2020-02-07","cited_by_count":24},{"id":"1707.06170","title":"Learning model-based planning from scratch","created":"2017-07-19","cited_by_count":22},{"id":"1912.02807","title":"Combining Q-Learning and Search with Amortized Value Estimates","created":"2019-12-05","cited_by_count":19},{"id":"1811.02696","title":"ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search","created":"2018-11-06","cited_by_count":12},{"id":"2010.05545","title":"Local Search for Policy Iteration in Continuous Control","created":"2020-10-12","cited_by_count":9},{"id":"1907.03687","title":"General non-linear Bellman equations","created":"2019-07-08","cited_by_count":8},{"id":"2002.08329","title":"Value-driven Hindsight Modelling","created":"2020-02-19","cited_by_count":6},{"id":"1508.04582","title":"Learning to Predict Independent of Span","created":"2015-08-19","cited_by_count":5}],"next_cursor":null}