{"list":"other","total":56,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"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":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"id":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"2110.01548","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","created":"2021-10-04","cited_by_count":302},{"id":"2007.03304","title":"Learning to Generate Novel Domains for Domain Generalization","created":"2020-07-07","cited_by_count":296},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1802.09464","title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research","created":"2018-02-26","cited_by_count":260},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170},{"id":"2206.13499","title":"Prompting Decision Transformer for Few-Shot Policy Generalization","created":"2022-06-27","cited_by_count":146},{"id":"2104.07749","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","created":"2021-04-15","cited_by_count":125},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125},{"id":"1812.07626","title":"Universal Successor Features Approximators","created":"2018-12-18","cited_by_count":103},{"id":"2007.02832","title":"Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning","created":"2020-07-06","cited_by_count":102},{"id":"2010.11876","title":"Error Bounds of Imitating Policies and Environments","created":"2020-10-22","cited_by_count":90},{"id":"2206.02829","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","created":"2022-06-06","cited_by_count":84},{"id":"2010.10814","title":"Improving Generalization in Reinforcement Learning with Mixture Regularization","created":"2020-10-21","cited_by_count":81},{"id":"2106.03400","title":"Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning","created":"2021-06-07","cited_by_count":79},{"id":"2205.13703","title":"Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters","created":"2022-05-27","cited_by_count":76},{"id":"2002.11089","title":"Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement","created":"2020-02-25","cited_by_count":60},{"id":"2003.13590","title":"Suphx: Mastering Mahjong with Deep Reinforcement Learning","created":"2020-03-30","cited_by_count":58},{"id":"2203.05818","title":"ZIN: When and How to Learn Invariance Without Environment Partition?","created":"2022-03-11","cited_by_count":58},{"id":"2002.11708","title":"Generalized Hindsight for Reinforcement Learning","created":"2020-02-26","cited_by_count":51},{"id":"2301.13616","title":"Anti-Exploration by Random Network Distillation","created":"2023-01-31","cited_by_count":50},{"id":"2106.06431","title":"Offline Reinforcement Learning as Anti-Exploration","created":"2021-06-11","cited_by_count":44},{"id":"2210.11287","title":"MoCoDA: Model-based Counterfactual Data Augmentation","created":"2022-10-20","cited_by_count":44},{"id":"2301.09819","title":"Model Agnostic Sample Reweighting for Out-of-Distribution Learning","created":"2023-01-24","cited_by_count":44},{"id":"1905.08786","title":"Maximum Entropy-Regularized Multi-Goal Reinforcement Learning","created":"2019-05-21","cited_by_count":40},{"id":"1910.11670","title":"Contextual Imagined Goals for Self-Supervised Robotic Learning","created":"2019-10-23","cited_by_count":40},{"id":"2204.13060","title":"Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning","created":"2022-04-27","cited_by_count":38},{"id":"2006.01096","title":"Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learning","created":"2020-06-01","cited_by_count":37},{"id":"2207.09081","title":"Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning","created":"2022-07-19","cited_by_count":34},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31},{"id":"1304.1574","title":"Generalization Bounds for Domain Adaptation","created":"2013-04-04","cited_by_count":27},{"id":"2111.14629","title":"Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions","created":"2021-11-29","cited_by_count":17},{"id":"2107.00306","title":"MHER: Model-based Hindsight Experience Replay","created":"2021-07-01","cited_by_count":15},{"id":"2110.14248","title":"Learning Domain Invariant Representations in Goal-conditioned Block MDPs","created":"2021-10-27","cited_by_count":12},{"id":"1804.03758","title":"Universal Successor Representations for Transfer Reinforcement Learning","created":"2018-04-11","cited_by_count":10}],"next_cursor":null}