{"list":"other","total":54,"rows":[{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"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":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"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":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"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":"1511.06295","title":"Policy Distillation","created":"2015-11-19","cited_by_count":440},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"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":"1910.11215","title":"RoboNet: Large-Scale Multi-Robot Learning","created":"2019-10-24","cited_by_count":270},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"1707.04175","title":"Distral: Robust Multitask Reinforcement Learning","created":"2017-07-13","cited_by_count":233},{"id":"2104.08212","title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","created":"2021-04-16","cited_by_count":229},{"id":"1912.02074","title":"AlgaeDICE: Policy Gradient from Arbitrary Experience","created":"2019-12-04","cited_by_count":188},{"id":"1511.06342","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","created":"2015-11-19","cited_by_count":178},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174},{"id":"1712.06924","title":"Safe Policy Improvement with Baseline Bootstrapping","created":"2017-12-19","cited_by_count":144},{"id":"2003.13661","title":"Multi-Task Reinforcement Learning with Soft Modularization","created":"2020-03-30","cited_by_count":143},{"id":"1809.04474","title":"Multi-task Deep Reinforcement Learning with PopArt","created":"2018-09-12","cited_by_count":141},{"id":"2011.10024","title":"Parrot: Data-Driven Behavioral Priors for Reinforcement Learning","created":"2020-11-19","cited_by_count":138},{"id":"2008.05556","title":"Model-Based Offline Planning","created":"2020-08-12","cited_by_count":129},{"id":"2104.07749","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","created":"2021-04-15","cited_by_count":125},{"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":"1503.04269","title":"An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning","created":"2015-03-14","cited_by_count":103},{"id":"1807.01473","title":"Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation","created":"2018-07-04","cited_by_count":101},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93},{"id":"1802.09081","title":"Temporal Difference Models: Model-Free Deep RL for Model-Based Control","created":"2018-02-25","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":"1810.07121","title":"Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation","created":"2018-10-16","cited_by_count":76},{"id":"2003.07305","title":"DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction","created":"2020-03-16","cited_by_count":71},{"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":"2002.11089","title":"Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement","created":"2020-02-25","cited_by_count":60},{"id":"2002.11708","title":"Generalized Hindsight for Reinforcement Learning","created":"2020-02-26","cited_by_count":51},{"id":"1711.09874","title":"Divide-and-Conquer Reinforcement Learning","created":"2017-11-27","cited_by_count":48},{"id":"1908.05451","title":"Mapping State Space using Landmarks for Universal Goal Reaching","created":"2019-08-15","cited_by_count":44},{"id":"1904.11455","title":"Ray Interference: a Source of Plateaus in Deep Reinforcement Learning","created":"2019-04-25","cited_by_count":40},{"id":"1904.05538","title":"Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight","created":"2019-04-11","cited_by_count":34},{"id":"2011.11235","title":"An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare","created":"2020-11-23","cited_by_count":34},{"id":"1810.00482","title":"Few-Shot Goal Inference for Visuomotor Learning and Planning","created":"2018-09-30","cited_by_count":30},{"id":"2010.07494","title":"Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control","created":"2020-10-15","cited_by_count":28},{"id":"1902.00528","title":"Competitive Experience Replay","created":"2019-02-01","cited_by_count":23},{"id":"1910.14055","title":"Policy Continuation with Hindsight Inverse Dynamics","created":"2019-10-30","cited_by_count":22},{"id":"1905.07866","title":"Reinforcement Learning without Ground-Truth State","created":"2019-05-20","cited_by_count":15},{"id":"2102.12962","title":"Bias-reduced Multi-step Hindsight Experience Replay for Efficient Multi-goal Reinforcement Learning","created":"2021-02-25","cited_by_count":4}],"next_cursor":null}