{"list":"other","total":58,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1711.05769","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","created":"2017-11-15","cited_by_count":898},{"id":"1801.01423","title":"Overcoming catastrophic forgetting with hard attention to the task","created":"2018-01-04","cited_by_count":681},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"1611.04717","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","created":"2016-11-15","cited_by_count":309},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1703.01310","title":"Count-Based Exploration with Neural Density Models","created":"2017-03-03","cited_by_count":257},{"id":"1703.08475","title":"Overcoming Catastrophic Forgetting by Incremental Moment Matching","created":"2017-03-24","cited_by_count":243},{"id":"2006.14769","title":"Supermasks in Superposition","created":"2020-06-26","cited_by_count":227},{"id":"1901.10995","title":"Go-Explore: a New Approach for Hard-Exploration Problems","created":"2019-01-30","cited_by_count":212},{"id":"2002.06038","title":"Never Give Up: Learning Directed Exploration Strategies","created":"2020-02-14","cited_by_count":212},{"id":"1905.12588","title":"Meta-Learning Representations for Continual Learning","created":"2019-05-29","cited_by_count":189},{"id":"1805.12369","title":"Reinforced Continual Learning","created":"2018-05-31","cited_by_count":186},{"id":"1806.07857","title":"RUDDER: Return Decomposition for Delayed Rewards","created":"2018-06-20","cited_by_count":173},{"id":"1507.00814","title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","created":"2015-07-03","cited_by_count":154},{"id":"2002.12292","title":"RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments","created":"2020-02-27","cited_by_count":135},{"id":"1809.05922","title":"Memory Efficient Experience Replay for Streaming Learning","created":"2018-09-16","cited_by_count":128},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116},{"id":"1807.11622","title":"Count-Based Exploration with the Successor Representation","created":"2018-07-31","cited_by_count":112},{"id":"1806.08568","title":"Continuous Learning in Single-Incremental-Task Scenarios","created":"2018-06-22","cited_by_count":109},{"id":"1909.09146","title":"Weighted Linear Bandits for Non-Stationary Environments","created":"2019-09-19","cited_by_count":86},{"id":"1703.01732","title":"Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning","created":"2017-03-06","cited_by_count":83},{"id":"2006.14389","title":"Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism","created":"2020-06-24","cited_by_count":76},{"id":"2103.05324","title":"A Simple Approach for Non-stationary Linear Bandits","created":"2021-03-09","cited_by_count":54},{"id":"2007.13904","title":"La-MAML: Look-ahead Meta Learning for Continual Learning","created":"2020-07-27","cited_by_count":52},{"id":"1802.03692","title":"Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Bandit","created":"2018-02-11","cited_by_count":50},{"id":"1706.08090","title":"Count-Based Exploration in Feature Space for Reinforcement Learning","created":"2017-06-25","cited_by_count":49},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45},{"id":"2106.02940","title":"Same State, Different Task: Continual Reinforcement Learning without Interference","created":"2021-06-05","cited_by_count":43},{"id":"1405.3316","title":"Optimal Exploration-Exploitation in a Multi-Armed-Bandit Problem with Non-stationary Rewards","created":"2014-05-13","cited_by_count":42},{"id":"2205.12258","title":"History Compression via Language Models in Reinforcement Learning","created":"2022-05-24","cited_by_count":39},{"id":"1805.10966","title":"Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization","created":"2018-05-28","cited_by_count":38},{"id":"2005.08158","title":"Optimizing for the Future in Non-Stationary MDPs","created":"2020-05-17","cited_by_count":37},{"id":"1904.10090","title":"Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning, Extended version","created":"2019-04-22","cited_by_count":36},{"id":"2009.14108","title":"Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution","created":"2020-09-29","cited_by_count":36},{"id":"2010.00373","title":"Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates","created":"2020-10-01","cited_by_count":34},{"id":"1707.09727","title":"Taming Non-stationary Bandits: A Bayesian Approach","created":"2017-07-31","cited_by_count":32},{"id":"2010.06498","title":"Cross-Domain Few-Shot Learning by Representation Fusion","created":"2020-10-13","cited_by_count":32},{"id":"1805.09365","title":"Learning Contextual Bandits in a Non-stationary Environment","created":"2018-05-23","cited_by_count":26},{"id":"2002.06306","title":"Jelly Bean World: A Testbed for Never-Ending Learning","created":"2020-02-15","cited_by_count":19},{"id":"2012.01399","title":"Convergence Proof for Actor-Critic Methods Applied to PPO and RUDDER","created":"2020-12-02","cited_by_count":19},{"id":"2202.05839","title":"Abstraction for Deep Reinforcement Learning","created":"2022-02-10","cited_by_count":19},{"id":"1902.00843","title":"A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning","created":"2019-02-03","cited_by_count":18},{"id":"2105.09452","title":"Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection","created":"2021-05-20","cited_by_count":18},{"id":"1905.03970","title":"Reinforcement Learning in Non-Stationary Environments","created":"2019-05-10","cited_by_count":10},{"id":"2006.12109","title":"Continual Learning in Recurrent Neural Networks","created":"2020-06-22","cited_by_count":10},{"id":"1906.03506","title":"Forward and Backward Knowledge Transfer for Sentiment Classification","created":"2019-06-08","cited_by_count":9},{"id":"2112.06625","title":"Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization","created":"2021-12-13","cited_by_count":5}],"next_cursor":null}