On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

28 December 2022

Papers citing "On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations"

22 / 22 papers shown

Title
Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network Jijia Liu Feng Gao Q. Liao Chao Yu Yu-Xiang Wang OffRL 70 0 0 01 Feb 2025
Marvel: Accelerating Safe Online Reinforcement Learning with Finetuned Offline Policy Keru Chen Honghao Wei Zhigang Deng Sen Lin OffRL OnRL 94 0 0 31 Dec 2024
Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal Guidance Renming Huang Shaochong Liu Yunqiang Pei Peng Wang Guoqing Wang Yang Yang Hengtao Shen OffRL 37 0 0 06 Sep 2024
FOSP: Fine-tuning Offline Safe Policy through World Models Chenyang Cao Yucheng Xin Silang Wu Longxiang He Zichen Yan Junbo Tan Xueqian Wang OffRL 61 0 0 06 Jul 2024
DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays Bo Xia Yilun Kong Yongzhe Chang Bo Yuan Zhiheng Li Xueqian Wang Bin Liang OffRL 48 3 0 05 Jun 2024
Tractable Function-Space Variational Inference in Bayesian Neural Networks Tim G. J. Rudner Zonghao Chen Yee Whye Teh Y. Gal 80 39 0 28 Dec 2023
Mitigating Estimation Errors by Twin TD-Regularized Actor and Critic for Deep Reinforcement Learning Junmin Zhong Ruofan Wu Jennie Si OffRL 11 1 0 07 Nov 2023
Imitation Bootstrapped Reinforcement Learning Hengyuan Hu Suvir Mirchandani Dorsa Sadigh 41 24 0 03 Nov 2023
Coherent Soft Imitation Learning Joe Watson Sandy H. Huang Nicholas Heess 32 11 0 25 May 2023
Learning and Adapting Agile Locomotion Skills by Transferring Experience Laura M. Smith J. Kew Tianyu Li Linda Luu Xue Bin Peng Sehoon Ha Jie Tan Sergey Levine 26 55 0 19 Apr 2023
Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot Tao Huang Kai-xiang Chen Bin Li Yunhui Liu Qingxu Dou 35 23 0 20 Feb 2023
Efficient Online Reinforcement Learning with Offline Data Philip J. Ball Laura M. Smith Ilya Kostrikov Sergey Levine OffRL OnRL 32 163 0 06 Feb 2023
Policy Expansion for Bridging Offline-to-Online Reinforcement Learning Haichao Zhang Weiwen Xu Haonan Yu CLL OffRL OnRL 40 62 0 02 Feb 2023
Semi-supervised Batch Learning From Logged Data Gholamali Aminian Armin Behnamnia R. Vega Laura Toni Chengchun Shi Hamid R. Rabiee Omar Rivasplata Miguel R. D. Rodrigues OffRL 26 0 0 15 Sep 2022
Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics Jun Jet Tai Jordan Terry M. Innocente J. Brusey N. Horri 21 1 0 22 Aug 2022
Offline Policy Comparison with Confidence: Benchmarks and Baselines Anurag Koul Mariano Phielipp Alan Fern OffRL 28 0 0 22 May 2022
Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching Yecheng Jason Ma Andrew Shen Dinesh Jayaraman Osbert Bastani OffRL 23 32 0 04 Feb 2022
Modeling Strong and Human-Like Gameplay with KL-Regularized Search Athul Paul Jacob David J. Wu Gabriele Farina Adam Lerer Hengyuan Hu A. Bakhtin Jacob Andreas Noam Brown 22 52 0 14 Dec 2021
Outcome-Driven Reinforcement Learning via Variational Inference Tim G. J. Rudner Vitchyr H. Pong R. McAllister Y. Gal Sergey Levine 32 20 0 20 Apr 2021
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment Philip J. Ball Cong Lu Jack Parker-Holder Stephen J. Roberts OffRL 21 40 0 12 Apr 2021
COMBO: Conservative Offline Model-Based Policy Optimization Tianhe Yu Aviral Kumar Rafael Rafailov Aravind Rajeswaran Sergey Levine Chelsea Finn OffRL 219 413 0 16 Feb 2021
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles Balaji Lakshminarayanan Alexander Pritzel Charles Blundell UQCV BDL 276 5,661 0 05 Dec 2016