{"list":"other","total":54,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"1603.00448","title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","created":"2016-03-01","cited_by_count":406},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284},{"id":"1802.09464","title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research","created":"2018-02-26","cited_by_count":260},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253},{"id":"2103.08050","title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization","created":"2021-03-14","cited_by_count":238},{"id":"2104.08212","title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","created":"2021-04-16","cited_by_count":229},{"id":"2002.08396","title":"Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning","created":"2020-02-19","cited_by_count":215},{"id":"2106.08909","title":"Offline RL Without Off-Policy Evaluation","created":"2021-06-16","cited_by_count":151},{"id":"2006.00979","title":"Acme: A Research Framework for Distributed Reinforcement Learning","created":"2020-06-01","cited_by_count":146},{"id":"2011.07213","title":"PLAS: Latent Action Space for Offline Reinforcement Learning","created":"2020-11-14","cited_by_count":133},{"id":"2008.05556","title":"Model-Based Offline Planning","created":"2020-08-12","cited_by_count":129},{"id":"1904.07854","title":"End-to-End Robotic Reinforcement Learning without Reward Engineering","created":"2019-04-16","cited_by_count":122},{"id":"2006.03647","title":"Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization","created":"2020-06-05","cited_by_count":120},{"id":"2103.16817","title":"Learning Generalizable Robotic Reward Functions from \"In-The-Wild\" Human Videos","created":"2021-03-31","cited_by_count":119},{"id":"2004.12570","title":"The Ingredients of Real-World Robotic Reinforcement Learning","created":"2020-04-27","cited_by_count":117},{"id":"2007.11091","title":"EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL","created":"2020-07-21","cited_by_count":115},{"id":"1809.01812","title":"Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency","created":"2018-09-06","cited_by_count":105},{"id":"2012.11547","title":"Offline Reinforcement Learning from Images with Latent Space Models","created":"2020-12-21","cited_by_count":95},{"id":"2207.10050","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","created":"2022-07-20","cited_by_count":89},{"id":"1911.05321","title":"IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data","created":"2019-11-13","cited_by_count":86},{"id":"2103.06326","title":"S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning","created":"2021-03-10","cited_by_count":85},{"id":"2010.14500","title":"COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning","created":"2020-10-27","cited_by_count":83},{"id":"2006.07217","title":"Deep Reinforcement and InfoMax Learning","created":"2020-06-12","cited_by_count":79},{"id":"2007.08202","title":"Provably Good Batch Reinforcement Learning Without Great Exploration","created":"2020-07-16","cited_by_count":77},{"id":"2011.13885","title":"Offline Learning from Demonstrations and Unlabeled Experience","created":"2020-11-27","cited_by_count":72},{"id":"1805.11686","title":"Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition","created":"2018-05-29","cited_by_count":69},{"id":"2102.02872","title":"Feedback in Imitation Learning: The Three Regimes of Covariate Shift","created":"2021-02-04","cited_by_count":68},{"id":"2202.01741","title":"How to Leverage Unlabeled Data in Offline Reinforcement Learning","created":"2022-02-03","cited_by_count":62},{"id":"1910.01077","title":"Task-Relevant Adversarial Imitation Learning","created":"2019-10-02","cited_by_count":45},{"id":"2008.05533","title":"Overcoming Model Bias for Robust Offline Deep Reinforcement Learning","created":"2020-08-12","cited_by_count":43},{"id":"2103.12656","title":"Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification","created":"2021-03-23","cited_by_count":38},{"id":"1911.00459","title":"Positive-Unlabeled Reward Learning","created":"2019-11-01","cited_by_count":37},{"id":"1810.00482","title":"Few-Shot Goal Inference for Visuomotor Learning and Planning","created":"2018-09-30","cited_by_count":30},{"id":"2107.07184","title":"MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning","created":"2021-07-15","cited_by_count":24},{"id":"2004.10190","title":"Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning","created":"2020-04-21","cited_by_count":23},{"id":"2012.06899","title":"Semi-supervised reward learning for offline reinforcement learning","created":"2020-12-12","cited_by_count":23},{"id":"1909.12200","title":"Scaling data-driven robotics with reward sketching and batch reinforcement learning","created":"2019-09-26","cited_by_count":18},{"id":"2106.05068","title":"Offline Inverse Reinforcement Learning","created":"2021-06-09","cited_by_count":14}],"next_cursor":null}