Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence

Recently, there are many efforts attempting to learn useful policies for continuous control in visual reinforcement learning (RL). In this scenario, it is important to learn a generalizable policy, as the testing environment may differ from the training environment, e.g., there exist distractors dur...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The Journal of artificial intelligence research Ročník 81; s. 1 - 42
Hlavní autoři: Lyu, Jiafei, Wan, Le, Li, Xiu, Lu, Zongqing
Médium: Journal Article
Jazyk:angličtina
Vydáno: San Francisco AI Access Foundation 2024
Témata:
Algorithms
ISSN:1076-9757, 1076-9757, 1943-5037
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Recently, there are many efforts attempting to learn useful policies for continuous control in visual reinforcement learning (RL). In this scenario, it is important to learn a generalizable policy, as the testing environment may differ from the training environment, e.g., there exist distractors during deployment. Many practical algorithms are proposed to handle this problem. However, to the best of our knowledge, none of them provide a theoretical understanding of what affects the generalization gap and why their proposed methods work. In this paper, we bridge this issue by theoretically answering the key factors that contribute to the generalization gap when the testing environment has distractors. Our theories indicate that minimizing the representation distance between training and testing environments, which aligns with human intuition, is the most critical for the benefit of reducing the generalization gap. Our theoretical results are supported by the empirical evidence in the DMControl Generalization Benchmark (DMC-GB).
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1076-9757
1076-9757
1943-5037
DOI:10.1613/jair.1.16422