Schrittwieser and colleagues: MuZero planning with a learned model

What changed

Planned with a learned reward/policy/value model and reported strong Atari and board-game results.

Scientific scope

The record is the exact twelve-author Nature paper. Claims remain confined to the reported games, training budgets and evaluation protocol; it does not establish general real-world planning, safety or domain-independent intelligence.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact twelve-author Nature paper. Claims remain confined to the reported games, training budgets and evaluation protocol; it does not establish general real-world planning, safety or domain-independent intelligence.

Contributors

• The named authors listed in the linked research record · SCIENCE: Complete source byline retained in the research record; this collective display does not merge person identities or measure labor shares.

• arXiv record and full text for MuZero
• Nature DOI for MuZero

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction