{"list":"other","total":67,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"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":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"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":"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":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"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":"2304.10573","title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","created":"2023-04-20","cited_by_count":325},{"id":"2110.01548","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","created":"2021-10-04","cited_by_count":302},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279},{"id":"2006.15134","title":"Critic Regularized Regression","created":"2020-06-26","cited_by_count":275},{"id":"1906.04733","title":"DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections","created":"2019-06-10","cited_by_count":254},{"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":"2106.12142","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","created":"2021-06-23","cited_by_count":193},{"id":"1912.02074","title":"AlgaeDICE: Policy Gradient from Arbitrary Experience","created":"2019-12-04","cited_by_count":188},{"id":"1912.05032","title":"Imitation Learning via Off-Policy Distribution Matching","created":"2019-12-10","cited_by_count":183},{"id":"2106.08909","title":"Offline RL Without Off-Policy Evaluation","created":"2021-06-16","cited_by_count":151},{"id":"2305.09836","title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning","created":"2023-05-16","cited_by_count":126},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125},{"id":"1905.12888","title":"Imitation Learning as $f$-Divergence Minimization","created":"2019-05-30","cited_by_count":123},{"id":"2002.09072","title":"GenDICE: Generalized Offline Estimation of Stationary Values","created":"2020-02-21","cited_by_count":122},{"id":"2106.10783","title":"OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation","created":"2021-06-21","cited_by_count":121},{"id":"2303.15810","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","created":"2023-03-28","cited_by_count":116},{"id":"2001.01866","title":"Reinforcement Learning via Fenchel-Rockafellar Duality","created":"2020-01-07","cited_by_count":100},{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95},{"id":"1910.12179","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning","created":"2019-10-27","cited_by_count":91},{"id":"2107.09003","title":"Constraints Penalized Q-learning for Safe Offline Reinforcement Learning","created":"2021-07-19","cited_by_count":91},{"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":"2406.09329","title":"Is Value Learning Really the Main Bottleneck in Offline RL?","created":"2024-06-13","cited_by_count":89},{"id":"2007.03438","title":"Off-Policy Evaluation via the Regularized Lagrangian","created":"2020-07-07","cited_by_count":86},{"id":"2204.08957","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","created":"2022-04-19","cited_by_count":71},{"id":"2001.11113","title":"GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values","created":"2020-01-29","cited_by_count":70},{"id":"2102.13185","title":"Off-Policy Imitation Learning from Observations","created":"2021-02-25","cited_by_count":70},{"id":"2206.03023","title":"How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression","created":"2022-06-07","cited_by_count":66},{"id":"2401.10700","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","created":"2024-01-19","cited_by_count":64},{"id":"2206.13464","title":"When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning","created":"2022-06-27","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":"2102.11492","title":"DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning","created":"2021-02-23","cited_by_count":48},{"id":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48},{"id":"2307.11620","title":"Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization","created":"2023-07-21","cited_by_count":43},{"id":"2407.20109","title":"Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning","created":"2024-07-29","cited_by_count":42},{"id":"2205.11027","title":"When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning","created":"2022-05-23","cited_by_count":31},{"id":"2305.15669","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","created":"2023-05-25","cited_by_count":29},{"id":"2110.07395","title":"Offline Reinforcement Learning with Soft Behavior Regularization","created":"2021-10-14","cited_by_count":28},{"id":"2102.09225","title":"Continuous Doubly Constrained Batch Reinforcement Learning","created":"2021-02-18","cited_by_count":27},{"id":"2310.04413","title":"Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-10-06","cited_by_count":24},{"id":"2306.13085","title":"Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting","created":"2023-06-22","cited_by_count":22},{"id":"1905.01072","title":"Deep Residual Reinforcement Learning","created":"2019-05-03","cited_by_count":21},{"id":"2311.02013","title":"SMORE: Score Models for Offline Goal-Conditioned Reinforcement Learning","created":"2023-11-03","cited_by_count":21},{"id":"2402.00348","title":"ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update","created":"2024-02-01","cited_by_count":21},{"id":"2111.05440","title":"Dealing with the Unknown: Pessimistic Offline Reinforcement Learning","created":"2021-11-09","cited_by_count":19},{"id":"2306.04220","title":"Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL","created":"2023-06-07","cited_by_count":18},{"id":"2301.12203","title":"SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning","created":"2023-01-28","cited_by_count":16},{"id":"2306.05726","title":"Iteratively Refined Behavior Regularization for Offline Reinforcement Learning","created":"2023-06-09","cited_by_count":10},{"id":"2406.08805","title":"A Dual Approach to Imitation Learning from Observations with Offline Datasets","created":"2024-06-13","cited_by_count":10},{"id":"2408.02165","title":"SelfBC: Self Behavior Cloning for Offline Reinforcement Learning","created":"2024-08-04","cited_by_count":3}],"next_cursor":null}