paper-with-me

Papers

Addressing Extrapolation Error in Deep Offline Reinforcement Learning

2021-01-01 · Caglar Gulcehre, Sergio Gómez Colmenarejo, Ziyu Wang, Jakub Sygnowski, Thomas Paine, Konrad Zolna, Yutian Chen, Matthew Hoffman, Razvan Pascanu, Nando de Freitas

Reinforcement learning (RL) encompasses both online and offline regimes. Unlike its online counterpart, offline RL agents are trained using logged-data only, without interaction with the environment. Therefore, offline RL is a promising direction for real-world applications, such as healthcare, where repeated interaction with environments is prohibitive. However, since offline RL losses often involve evaluating state-action pairs not well-covered by training data, they can suffer due to the errors introduced when the function approximator attempts to extrapolate those pairs' value. These errors can be compounded by bootstrapping when the function approximator overestimates, leading the value function to *grow unbounded*, thereby crippling learning. In this paper, we introduce a three-part solution to combat extrapolation errors: (i) behavior value estimation, (ii) ranking regularization, and (iii) reparametrization of the value function. We provide ample empirical evidence on the effectiveness of our method, showing state of the art performance on the RL Unplugged (RLU) ATARI dataset. Furthermore, we introduce new datasets for bsuite as well as partially observable DeepMind Lab environments, on which our method outperforms state of the art offline RL algorithms.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Learning from Sparse Offline Datasets via Conservative Density Estimation

2024-01-16 · Zhepeng Cen, Zuxin Liu, Zitong Wang, Yihang Yao 외

Offline reinforcement learning (RL) offers a promising direction for learning policies from pre-collected datasets without requiring further interactions with the environment. However, existing methods struggle to handle…

D4RLDensity EstimationOffline RLReinforcement Learning (RL)

Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning

2021-06-07 · NeurIPS 2021 12 · Yiqin Yang, Xiaoteng Ma, Chenghao Li, Zewu Zheng 외

Learning from datasets without interaction with environments (Offline Learning) is an essential step to apply Reinforcement Learning (RL) algorithms in real-world scenarios. However, compared with the single-agent counte…

Multi-agent Reinforcement LearningOffline RLQ-Learningreinforcement-learning+3

Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data

2025-07-11 · Jeonghye Kim, Yongjae Shin, Whiyoung Jung, Sunghoon Hong 외 arxiv

Reinforcement learning with offline data suffers from Q-value extrapolation errors. To address this issue, we first demonstrate that linear extrapolation of the Q-function beyond the data range is particularly problemati…

Reinforcement Learning

Model-Based Offline Reinforcement Learning with Adversarial Data Augmentation

2025-03-26 · Hongye Cao, Fan Feng, Jing Huo, Shangdong Yang 외

Model-based offline Reinforcement Learning (RL) constructs environment models from offline datasets to perform conservative policy optimization. Existing approaches focus on learning state transitions through ensemble mo…

D4RLData AugmentationOffline RLreinforcement-learning+2

Offline Reinforcement Learning with On-Policy Q-Function Regularization

2023-07-25 · Laixi Shi, Robert Dadashi, Yuejie Chi, Pablo Samuel Castro 외

The core challenge of offline reinforcement learning (RL) is dealing with the (potentially catastrophic) extrapolation error induced by the distribution shift between the history dataset and the desired policy. A large p…

D4RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)