HarmonyFidelisHarmonyFidelis
Login
Skip to content
AURA
LearnConfigurePublic programs
Learn

First principles

LearningInference

Mechanisms

RepresentationsContext & memoryArchitecturesDiffusion

Advanced research

Reasoning & agentsWorld modelsAGI & ASIEvaluation

Explore each space independently. More detail is always within reach.

Aura home
AuraUnderstand AIWorld models

Predicting to choose an action

Explore longer horizons and the risk of inaccurate predictions.

EssentialsExperimentGo deeper
Scientific sources
Definition

A world model predicts useful aspects of an environment’s evolution. DreamerV3 learns behaviours on imagined trajectories in a latent model. MuZero combines a learned decision-relevant model with tree search.

Equation

Gₕ = Σₜ₌₁ʰ γᵗ⁻¹ rₜ

Gₕ sums rewards r over h steps with discount factor γ. Our toy sets γ = 1 and compares two deterministic paths.

Assumptions and notation

Gₕ sums rewards r over h steps with discount factor γ. Our toy sets γ = 1 and compares two deterministic paths.

Limits of interpretation

These systems use predictions differently. Model errors can accumulate; looking farther ahead does not guarantee a better decision. Our toy does not run either algorithm.

DreamerV3 learns a policy on imagined latent trajectories. MuZero predicts reward, value and policy for tree search. Reconstructing every detail of the world is not their common objective.

On this page

DefinitionEquationAssumptions and notationLimits of interpretationScientific sources
Essentials

Scientific sources

  • Hafner et al. · 2023Mastering Diverse Domains through World ModelsDreamerV3 · arXiv v2 · 2024
    Original publication
  • Schrittwieser et al. · 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned ModelarXiv v2 · 2020
    Original publication

Teaching synthesis of the cited sources. Published results remain tied to their tasks, protocols and budgets.

Explore nextAGI & ASIInference

Search Aura

18 results

LearnLearning, then using a modelSeparate learned parameters from information supplied with a request.
LearnFrom context to the next tokenSeparate the model’s probabilities from the rule that selects an output.
LearnFrom text to representationsUnderstand why words become vectors without equating a vector with human meaning.
LearnWhat kind of memory?Separate working context, recurrent state, learned parameters and persistent storage.
LearnTransformers: understanding attentionCompare architectures, training methods and complete systems at the right level.
LearnGenerating by denoisingDistinguish corruption during learning from progressive generation.
LearnFrom a model to a system that actsUnderstand the harness around a model and its tools.
LearnPredicting to choose an actionExplore longer horizons and the risk of inaccurate predictions.
LearnDefinitions, not a single verdictExamine generality, performance and adaptation before applying a label.
LearnWhat can a result establish?Move from a convincing impression to a reproducible comparison.
ConfigurePrepare a ChatGPT projectA clear objective, useful context and instructions you can actually use.
ConfigureChoose for your taskStart with your needs. Compare access and outcomes without a universal model ranking.
ConfigureMake your request verifiableTurn an intention into an objective, context and success criteria.
ConfigurePut the right information in the right placeDistinguish working rules, task resources and memory managed by the product.
ConfigurePrepare a development environmentDefine the model’s role, harness capabilities and the access you actually need.
ConfigureCompose a development workflowOrganise preparation, changes, verification and reporting. Reuse the steps that help.
ConfigurePrepare a mission, then check the resultA reproducible example, a checklist and a record of your observations.
Public programsTentacularPublicly available uses, features and resources.