Can I read Towards Robust Zero-Shot Reinforcement Learning on EtoBox?

Towards Robust Zero-Shot Reinforcement Learning by Kexin Zheng & Lauriane Teyssier & Yinan Zheng & Yu Luo & Xiayuan Zhan is a book available to read on EtoBox.

What is Towards Robust Zero-Shot Reinforcement Learning about?

arXiv:2510.15382v1 [cs.LG] 17 Oct 2025AbstractThe recent development of zero-shot reinforcement learning (RL) has openeda new avenue for learning pre-trained generalist policies that can adapt to arbitrary new tasks in a zero-shot manner. While the popular Forward-Backwardrepresentations (FB) and related methods have shown promise in zero-shot RL,we empirically found that their modeling lacks expressivity and that extrapolation errors caused by out-of-distribution (OOD) actions during offline learningsometimes lead to biased representations, ultimately resulting in suboptimal performance. To address these issues, we propose Behavior-REgularizEd Zero-shotRL with Expressivity enhancement (BREEZE), an upgraded FB-based frameworkthat simultaneously enhances learning stability, policy extraction capability, andrepresentation learning quality. BREEZE introduces behavioral regularizationin zero-shot RL policy learning, transforming policy optimization into a stablein-sample learning paradigm. Additionally, BREEZE extracts the policy usinga task-conditioned diffusion model, enabling the generation of high-quality andmultimodal action distributions in zero-shot RL settings. Moreover, BRE

Author

Kexin Zheng & Lauriane Teyssier & Yinan Zheng & Yu Luo & Xiayuan Zhan

Published

2025

Language

EN