A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning

The generalization of model-based reinforcement learning (MBRL) methods to environments with unseen transition dynamics is an important yet challenging problem. Existing methods try to extract environment-specified information \(Z\) from past transition segments to make the dynamics prediction model...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-06
Hauptverfasser: Guo, Jixian, Gong, Mingming, Tao, Dacheng
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The generalization of model-based reinforcement learning (MBRL) methods to environments with unseen transition dynamics is an important yet challenging problem. Existing methods try to extract environment-specified information \(Z\) from past transition segments to make the dynamics prediction model generalizable to different dynamics. However, because environments are not labelled, the extracted information inevitably contains redundant information unrelated to the dynamics in transition segments and thus fails to maintain a crucial property of \(Z\): \(Z\) should be similar in the same environment and dissimilar in different ones. As a result, the learned dynamics prediction function will deviate from the true one, which undermines the generalization ability. To tackle this problem, we introduce an interventional prediction module to estimate the probability of two estimated \(\hat{z}_i, \hat{z}_j\) belonging to the same environment. Furthermore, by utilizing the \(Z\)'s invariance within a single environment, a relational head is proposed to enforce the similarity between \(\hat{{Z}}\) from the same environment. As a result, the redundant information will be reduced in \(\hat{Z}\). We empirically show that \(\hat{{Z}}\) estimated by our method enjoy less redundant information than previous methods, and such \(\hat{{Z}}\) can significantly reduce dynamics prediction errors and improve the performance of model-based RL methods on zero-shot new environments with unseen dynamics. The codes of this method are available at \url{https://github.com/CR-Gjx/RIA}.
ISSN:2331-8422