Timezone: »

 
Poster
A Mixture Of Surprises for Unsupervised Reinforcement Learning
Andrew Zhao · Matthieu Lin · Yangguang Li · Yong-jin Liu · Gao Huang

@
Unsupervised reinforcement learning aims at learning a generalist policy in a reward-free manner for fast adaptation to downstream tasks. Most of the existing methods propose to provide an intrinsic reward based on surprise. Maximizing or minimizing surprise drives the agent to either explore or gain control over its environment. However, both strategies rely on a strong assumption: the entropy of the environment's dynamics is either high or low. This assumption may not always hold in real-world scenarios, where the entropy of the environment's dynamics may be unknown. Hence, choosing between the two objectives is a dilemma. We propose a novel yet simple mixture of policies to address this concern, allowing us to optimize an objective that simultaneously maximizes and minimizes the surprise. Concretely, we train one mixture component whose objective is to maximize the surprise and another whose objective is to minimize the surprise. Hence, our method does not make assumptions about the entropy of the environment's dynamics. We call our method a $\textbf{M}\text{ixture }\textbf{O}\text{f }\textbf{S}\text{urprise}\textbf{S}$ (MOSS) for unsupervised reinforcement learning. Experimental results show that our simple method achieves state-of-the-art performance on the URLB benchmark, outperforming previous pure surprise maximization-based objectives. Our code is available at: https://github.com/LeapLabTHU/MOSS.
Keywords: Unsupervised Reinforcement Learning
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Andrew Zhao (Tsinghua University)

Andrew Zhao is a PhD student at Tsinghua University. He obtained his masters degree from USC in 2020, and undergrad degree from UBC in 2017. His research interests are in machine learning and reinforcement learning.

Matthieu Lin (Tsinghua University, Tsinghua University)
Yangguang Li (SenseTime)
Yong-jin Liu (Tsinghua University, Tsinghua University)
Gao Huang (Cornell University)

More from the Same Authors