{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"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":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"2109.00137","title":"Implicit Behavioral Cloning","created":"2021-09-01","cited_by_count":452},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304},{"id":"2106.05091","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","created":"2021-06-09","cited_by_count":302},{"id":"1710.04615","title":"Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation","created":"2017-10-12","cited_by_count":289},{"id":"2006.15134","title":"Critic Regularized Regression","created":"2020-06-26","cited_by_count":275},{"id":"1810.02890","title":"HG-DAgger: Interactive Imitation Learning with Human Experts","created":"2018-10-05","cited_by_count":266},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260},{"id":"1811.02790","title":"RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation","created":"2018-11-07","cited_by_count":204},{"id":"2010.13611","title":"OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning","created":"2020-10-26","cited_by_count":166},{"id":"1701.06049","title":"Interactive Learning from Policy-Dependent Human Feedback","created":"2017-01-21","cited_by_count":158},{"id":"1709.10163","title":"Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces","created":"2017-09-28","cited_by_count":123},{"id":"2003.06085","title":"Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations","created":"2020-03-13","cited_by_count":115},{"id":"2012.06733","title":"Human-in-the-Loop Imitation Learning using Remote Teleoperation","created":"2020-12-12","cited_by_count":112},{"id":"2109.08273","title":"ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning","created":"2021-09-17","cited_by_count":108},{"id":"1807.08364","title":"EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning","created":"2018-07-22","cited_by_count":100},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89},{"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":"2010.14500","title":"COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning","created":"2020-10-27","cited_by_count":83},{"id":"2011.13885","title":"Offline Learning from Demonstrations and Unlabeled Experience","created":"2020-11-27","cited_by_count":72},{"id":"2006.14091","title":"Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferences","created":"2020-06-24","cited_by_count":71},{"id":"1802.01744","title":"Shared Autonomy via Deep Reinforcement Learning","created":"2018-02-06","cited_by_count":66},{"id":"2006.13888","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","created":"2020-06-24","cited_by_count":57},{"id":"2211.00600","title":"Interactive Imitation Learning in Robotics: A Survey","created":"2022-10-31","cited_by_count":55},{"id":"1503.07619","title":"Shared Autonomy via Hindsight Optimization","created":"2015-03-26","cited_by_count":46},{"id":"1909.09906","title":"Leveraging Human Guidance for Deep Reinforcement Learning Tasks","created":"2019-09-21","cited_by_count":42},{"id":"2105.12949","title":"A Survey on Interactive Reinforcement Learning: Design Principles and Open Challenges","created":"2021-05-27","cited_by_count":41},{"id":"2108.05382","title":"Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback","created":"2021-08-11","cited_by_count":35},{"id":"2110.03316","title":"Correct Me if I am Wrong: Interactive Learning for Robotic Manipulation","created":"2021-10-07","cited_by_count":24},{"id":"2210.08073","title":"Eliciting Compatible Demonstrations for Multi-Human Imitation Learning","created":"2022-10-14","cited_by_count":23},{"id":"1703.07019","title":"Continuous Integration, Delivery and Deployment: A Systematic Review on Approaches, Tools, Challenges and Practices","created":"2017-03-21","cited_by_count":22},{"id":"2210.15206","title":"Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Vision","created":"2022-10-27","cited_by_count":13},{"id":"2208.00565","title":"Modeling Human Response to Robot Errors for Timely Error Detection","created":"2022-08-01","cited_by_count":7},{"id":"1503.05451","title":"Autonomy Infused Teleoperation with Application to BCI Manipulation","created":"2015-03-18","cited_by_count":6}],"next_cursor":null}