AWhat changed
Learned deterministic-plus-stochastic recurrent latent dynamics from pixel observations and used online latent-space action planning, with latent overshooting to train multi-step predictions.
Scientific scope
Learned deterministic-plus-stochastic recurrent latent dynamics from pixel observations and used online latent-space action planning, with latent overshooting to train multi-step predictions. Distinct from Dreamer's imagined-policy training: PlaNet selects actions through online planning. Inherits state-space models and model-predictive control. Simulated-control efficiency does not establish exact physical dynamics, unrestricted long-horizon planning, transfer or real-world robot autonomy.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Distinct from Dreamer's imagined-policy training: PlaNet selects actions through online planning. Inherits state-space models and model-predictive control. Simulated-control efficiency does not establish exact physical dynamics, unrestricted long-horizon planning, transfer or real-world robot autonomy.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
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