{"list":"other","total":68,"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":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"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":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"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":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"1805.08296","title":"Data-Efficient Hierarchical Reinforcement Learning","created":"2018-05-21","cited_by_count":455},{"id":"2004.02857","title":"Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments","created":"2020-04-06","cited_by_count":441},{"id":"1910.11956","title":"Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning","created":"2019-10-25","cited_by_count":384},{"id":"1703.01161","title":"FeUdal Networks for Hierarchical Reinforcement Learning","created":"2017-03-03","cited_by_count":337},{"id":"1903.01973","title":"Learning Latent Plans from Play","created":"2019-03-05","cited_by_count":316},{"id":"1708.02596","title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","created":"2017-08-08","cited_by_count":297},{"id":"1604.06057","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","created":"2016-04-20","cited_by_count":286},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"1710.11252","title":"Stochastic Variational Video Prediction","created":"2017-10-30","cited_by_count":234},{"id":"1803.00653","title":"Semi-parametric Topological Memory for Navigation","created":"2018-03-01","cited_by_count":209},{"id":"2005.12256","title":"Neural Topological SLAM for Visual Navigation","created":"2020-05-25","cited_by_count":195},{"id":"1906.05253","title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","created":"2019-06-12","cited_by_count":194},{"id":"2112.10751","title":"RvS: What is Essential for Offline RL via Supervised Learning?","created":"2021-12-20","cited_by_count":185},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"2010.13611","title":"OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning","created":"2020-10-26","cited_by_count":166},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162},{"id":"1911.08453","title":"Planning with Goal-Conditioned Policies","created":"2019-11-19","cited_by_count":149},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125},{"id":"2304.01203","title":"Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning","created":"2023-04-03","cited_by_count":121},{"id":"2301.02328","title":"Extreme Q-Learning: MaxEnt RL without Entropy","created":"2023-01-05","cited_by_count":116},{"id":"1807.11622","title":"Count-Based Exploration with the Successor Representation","created":"2018-07-31","cited_by_count":112},{"id":"2007.02832","title":"Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning","created":"2020-07-06","cited_by_count":102},{"id":"1802.09081","title":"Temporal Difference Models: Model-Free Deep RL for Model-Based Control","created":"2018-02-25","cited_by_count":89},{"id":"1810.04586","title":"The Laplacian in RL: Learning Representations with Efficient Approximations","created":"2018-10-10","cited_by_count":86},{"id":"1909.05829","title":"Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation","created":"2019-09-12","cited_by_count":83},{"id":"1806.05767","title":"Motion Planning Networks","created":"2018-06-14","cited_by_count":80},{"id":"1911.01417","title":"Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards","created":"2019-11-04","cited_by_count":78},{"id":"2011.12491","title":"World Model as a Graph: Learning Latent Landmarks for Planning","created":"2020-11-25","cited_by_count":69},{"id":"1907.08225","title":"Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery","created":"2019-07-18","cited_by_count":68},{"id":"2304.04782","title":"Reinforcement Learning from Passive Data via Latent Intentions","created":"2023-04-10","cited_by_count":68},{"id":"2002.11089","title":"Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement","created":"2020-02-25","cited_by_count":60},{"id":"2210.08323","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","created":"2022-10-15","cited_by_count":59},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57},{"id":"1906.04279","title":"Exploration via Hindsight Goal Generation","created":"2019-06-10","cited_by_count":54},{"id":"2002.11708","title":"Generalized Hindsight for Reinforcement Learning","created":"2020-02-26","cited_by_count":51},{"id":"2007.07170","title":"Goal-Aware Prediction: Learning to Model What Matters","created":"2020-07-14","cited_by_count":45},{"id":"2105.13345","title":"Adversarial Intrinsic Motivation for Reinforcement Learning","created":"2021-05-27","cited_by_count":40},{"id":"1911.07224","title":"Learning from Trajectories via Subgoal Discovery","created":"2019-11-03","cited_by_count":28},{"id":"1805.08180","title":"Hierarchical Reinforcement Learning with Hindsight","created":"2018-05-21","cited_by_count":26},{"id":"2301.02099","title":"Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping","created":"2023-01-05","cited_by_count":25},{"id":"2111.09858","title":"Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning","created":"2021-11-18","cited_by_count":23},{"id":"2306.14069","title":"Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets","created":"2023-06-24","cited_by_count":22},{"id":"2006.00900","title":"PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goals","created":"2020-06-01","cited_by_count":21},{"id":"2301.12130","title":"Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learning","created":"2023-01-28","cited_by_count":16},{"id":"2302.06884","title":"Conservative State Value Estimation for Offline Reinforcement Learning","created":"2023-02-14","cited_by_count":9},{"id":"2410.20312","title":"Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model","created":"2024-10-27","cited_by_count":4}],"next_cursor":null}