Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learning
arxiv(2024)
摘要
In this work, we address the challenge of zero-shot generalization (ZSG) in
Reinforcement Learning (RL), where agents must adapt to entirely novel
environments without additional training. We argue that understanding and
utilizing contextual cues, such as the gravity level of the environment, is
critical for robust generalization, and we propose to integrate the learning of
context representations directly with policy learning. Our algorithm
demonstrates improved generalization on various simulated domains,
outperforming prior context-learning techniques in zero-shot settings. By
jointly learning policy and context, our method acquires behavior-specific
context representations, enabling adaptation to unseen environments and marks
progress towards reinforcement learning systems that generalize across diverse
real-world tasks. Our code and experiments are available at
https://github.com/tidiane-camaret/contextual_rl_zero_shot.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要