Methods › Reinforcement Learning › Board Game Models › MuZero

MuZero

46 papers tagged archive 2025-07-28

Introduced by Julian Schrittwieser et al. in Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

MuZero is a model-based reinforcement learning algorithm. It builds upon AlphaZero's search and search-based policy iteration algorithms, but incorporates a learned model into the training procedure.

The main idea of the algorithm is to predict those aspects of the future that are directly relevant for planning. The model receives the observation (e.g. an image of the Go board or the Atari screen) as an input and transforms it into a hidden state. The hidden state is then updated iteratively by a recurrent process that receives the previous hidden state and a hypothetical next action. At every one of these steps the model predicts the policy (e.g. the move to play), value function (e.g. the predicted winner), and immediate reward (e.g. the points scored by playing a move). The model is trained end-to-end, with the sole objective of accurately estimating these three important quantities, so as to match the improved estimates of policy and value generated by search as well as the observed reward.

There is no direct constraint or requirement for the hidden state to capture all information necessary to reconstruct the original observation, drastically reducing the amount of information the model has to maintain and predict; nor is there any requirement for the hidden state to match the unknown, true state of the environment; nor any other constraints on the semantics of state. Instead, the hidden states are free to represent state in whatever way is relevant to predicting current and future values and policies. Intuitively, the agent can invent, internally, the rules or dynamics that lead to most accurate planning.

PaperSource

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 18 in the graph, strongest link: mentioned on GitHub). This answer is about arXiv:1911.08265, the paper the archive credits with this method.

Origin paper of this answer, arXiv:1911.08265 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified (of 64 harvested samples) · 62 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 46 · with a code link: 23 · where Syntology ran a sample: 8 (7 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (8 of 46 tagged: 7 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 46 of 46, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 38 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
reinforcement-learning21
Reinforcement Learning (RL)19
Model-based Reinforcement Learning18
Reinforcement Learning15
Atari Games8
Board Games7
Decision Making6
Continuous Control5
Deep Reinforcement Learning5
Game of Go5
continuous-control4
model4
Atari Games 100k3
Offline RL3
Representation Learning3
Computational Efficiency2
Meta-Learning2
Starcraft2
Benchmarking1
Chatbot1

Usage over time archive 2025-07-28

Papers per year tagged with MuZero: 2019 to 2025, peak 13 13 0 2019: 1 paper 2019 2020: 5 papers 2020 2021: 13 papers 2021 2022: 9 papers 2022 2023: 8 papers 2023 2024: 7 papers 2024 2025: 3 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (46 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Board Game Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections