# OptionZero: Planning with Learned Options

arXiv: https://arxiv.org/abs/2502.16634 · HTML: https://mlsanity.com/paper/2502.16634/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods.
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 23 Feb 2025.

## Placed in

- Deep reinforcement learning methods / [RL for games and combinatorial optimization](https://mlsanity.com/deeprl/rl-for-games-and-combinatorial-optimization/)

## Builds on (most cited first, 25 of 25)

- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [The Option-Critic Architecture](https://mlsanity.com/paper/1609.05140/) (2016)
- [Mastering Atari Games with Limited Data](https://mlsanity.com/paper/2111.00210/) (2021)
- [Learning and Planning in Complex Action Spaces](https://mlsanity.com/paper/2104.06303/) (2021)
- [Muesli: Combining Improvements in Policy Optimization](https://mlsanity.com/paper/2104.06159/) (2021)
- [Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning](https://mlsanity.com/paper/1702.06054/) (2017)
- [Strategic Attentive Writer for Learning Macro-Actions](https://mlsanity.com/paper/1606.04695/) (2016)
- [MuZero with Self-competition for Rate Control in VP9 Video Compression](https://mlsanity.com/paper/2202.06626/) (2022)
- [Discovery of Options via Meta-Learned Subgoals](https://mlsanity.com/paper/2102.06741/) (2021)
- [Subgoal Search For Complex Reasoning Tasks](https://mlsanity.com/paper/2108.11204/) (2021)
- [Finding Options that Minimize Planning Time](https://mlsanity.com/paper/1810.07311/) (2018)
- [Hierarchical Imitation Learning with Vector Quantized Models](https://mlsanity.com/paper/2301.12962/) (2023)
- [Deep Reinforcement Learning With Macro-Actions](https://mlsanity.com/paper/1606.04615/) (2016)
- [MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games](https://mlsanity.com/paper/2310.11305/) (2023)
- [Visualizing MuZero Models](https://mlsanity.com/paper/2102.12924/) (2021)
- [On the Role of Weight Sharing During Deep Option Learning](https://mlsanity.com/paper/1912.13408/) (2019)
- [What model does MuZero learn?](https://mlsanity.com/paper/2306.00840/) (2023)
- [LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework](https://mlsanity.com/paper/2310.03342/) (2023)
- [Hybrid Search for Efficient Planning with Completeness Guarantees](https://mlsanity.com/paper/2310.12819/) (2023)
- [Optimizing Memory Mapping Using Deep Reinforcement Learning](https://mlsanity.com/paper/2305.07440/) (2023)
- [Iterative Option Discovery for Planning, by Planning](https://mlsanity.com/paper/2310.01569/) (2023)
- [Demystifying MuZero Planning: Interpreting the Learned Model](https://mlsanity.com/paper/2411.04580/) (2024)

## Built on by (most cited first, 2 of 2)

- [Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2505.12737/) (2025)
- [Toward Agents That Reason About Their Computation](https://mlsanity.com/paper/2510.22833/) (2025)

## Abstract (arXiv)

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.