OptionZero: Planning with Learned Options

Po-Wei Huang, Pei-Chiun Peng, Hung Guei, Ti-Rong Wu

Keywords: Option, Semi-MDP, MuZero, MCTS, Planning, Reinforcement Learning

TL;DR: This paper presents OptionZero, a method that integrates options into the MuZero algorithm, which autonomously discovers options through self-play games and utilizes options during planning.

Abstract:

Planning with options -- a sequence of primitive actions -- has been shown effective in reinforcement learning within complex environments. Previous studies have focused on planning with predefined options or learned options through expert demonstration data.
Inspired by MuZero, which learns superhuman heuristics without any human knowledge, we propose a novel approach, named *OptionZero*. OptionZero incorporates an *option network* into MuZero, providing autonomous discovery of options through self-play games. Furthermore, we modify the dynamics network to provide environment transitions when using options, allowing searching deeper under the same simulation constraints. Empirical experiments conducted in 26 Atari games demonstrate that OptionZero outperforms MuZero, achieving a 131.58% improvement in mean human-normalized score. Our behavior analysis shows that OptionZero not only learns options but also acquires strategic skills tailored to different game characteristics. Our findings show promising directions for discovering and using options in planning. Our code is available at https://rlg.iis.sinica.edu.tw/papers/optionzero.

Primary Area: reinforcement learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 10733