paper-with-me

홈 › Papers

BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning

2024-07-15 · Haohong Lin, Wenhao Ding, Jian Chen, Laixi Shi, Jiacheng Zhu, Bo Li, Ding Zhao

Offline model-based reinforcement learning (MBRL) enhances data efficiency by utilizing pre-collected datasets to learn models and policies, especially in scenarios where exploration is costly or infeasible. Nevertheless, its performance often suffers from the objective mismatch between model and policy learning, resulting in inferior performance despite accurate model predictions. This paper first identifies the primary source of this mismatch comes from the underlying confounders present in offline data for MBRL. Subsequently, we introduce \textbf{B}ilin\textbf{E}ar \textbf{CAUS}al r\textbf{E}presentation~(BECAUSE), an algorithm to capture causal representation for both states and actions to reduce the influence of the distribution shift, thus mitigating the objective mismatch problem. Comprehensive evaluations on 18 tasks that vary in data quality and environment context demonstrate the superior performance of BECAUSE over existing offline RL algorithms. We show the generalizability and robustness of BECAUSE under fewer samples or larger numbers of confounders. Additionally, we offer theoretical analysis of BECAUSE to prove its error bound and sample efficiency when integrating causal representation into offline MBRL.

📄 PDF Abstract BibTeX arXiv:2407.10967

Code (0)

등록된 구현이 없습니다.

Tasks

Model-based Reinforcement LearningOffline RL

Similar Papers 제목 키워드 기반

Safety-aware Causal Representation for Trustworthy Offline Reinforcement Learning in Autonomous Driving

2023-10-31 · Haohong Lin, Wenhao Ding, Zuxin Liu, Yaru Niu 외

In the domain of autonomous driving, the offline Reinforcement Learning~(RL) approaches exhibit notable efficacy in addressing sequential decision-making problems from offline datasets. However, maintaining safety in div…

Autonomous DrivingAutonomous VehiclesDecision MakingOffline RL+4

Generalizable Information Theoretic Causal Representation

2022-02-17 · Mengyue Yang, Xinyu Cai, Furui Liu, Xu Chen 외

It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems. Existing learning approaches …

counterfactualimage-classificationImage ClassificationRecommendation Systems+1

Informative Robust Causal Representation for Generalizable Deep Learning

2021-09-29 · Mengyue Yang, Furui Liu, Xu Chen, Zhitang Chen 외

In many real-world scenarios, such as image classification and recommender systems, it is evidence that representation learning can improve model's performance over multiple downstream tasks. Existing learning approaches…

counterfactualDeep Learningimage-classificationImage Classification+2

Unifying Causal Reinforcement Learning: Survey, Taxonomy, Algorithms and Applications

2025-12-19 · Cristiano da Costa Cunha, Wei Liu, Tim French, Ajmal Mian arxiv

Integrating causal inference (CI) with reinforcement learning (RL) has emerged as a powerful paradigm to address critical limitations in classical RL, including low explainability, lack of robustness and generalization f…

Representation LearningReinforcement LearningTransfer LearningCausal Inference

Bilinear Convolution Decomposition for Causal RL Interpretability

2024-12-01 · Narmeen Oozeer, Sinem Erisken, Alice Rigg

Efforts to interpret reinforcement learning (RL) models often rely on high-level techniques such as attribution or probing, which provide only correlational insights and coarse causal control. This work proposes replacin…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)