New: the Timeline is live. Track world model releases, papers, and benchmark updates in real time.
world-models.io
The Knowledge Hub for AI World Models

Value Prediction Network

The Value Prediction Network (VPN) learns an abstract world model optimized for value prediction, performing planning in a learned abstract state space.

robotics model-based-rl simulation embodied-ai

Key Attributes

Static HTML snapshot of the model record for crawlers and no-JS readers.

AttributeValue
ModelValue Prediction Network (VPN)
Lab / OrganizationDeepMind
CategoryModel-Based RL
SubtypeValue-Targeted Dynamics Model
World Model TypeValue-focused abstract dynamics
Primary DomainPlanning / Games
ArchitectureAbstract state transition model with value and reward prediction heads
ModalityVisual / Abstract states
Training MethodEnd-to-end training with value and reward prediction targets
Statusfoundational
Year2017
Performance Index43/100 (medium confidence, v1.1)

About Value Prediction Network (VPN)

Main editorial body preserved directly in static HTML.

The Value Prediction Network learns abstract state dynamics optimized for predicting future rewards and values rather than reconstructing raw observations. It performs multi-step planning in abstract space, rolling forward predictions of value through learned transitions. This approach avoids the pitfalls of pixel-level prediction while retaining the benefits of model-based planning. VPN showed that models optimized directly for value prediction can outperform both model-free methods and models that predict observations.

Value Prediction Network (VPN) is a value-focused abstract dynamics developed by University of Michigan / Google Brain in 2017 for planning / games.

Editorial Snapshot

Short extractable facts for answer engines and no-JS readers.

SignalValue
DefinitionValue Prediction Network (VPN) is a value-focused abstract dynamics developed by University of Michigan / Google Brain in 2017 for planning / games.
Short DescriptionA neural network that learns to plan by predicting future values and rewards through abstract state transitions, without reconstructing observations.
Benchmark Rows1
FAQ Entries1
Related Models2
Related Guides0
Related Research Topics1
Last Updated2026-01-15

Notable Features

Key capabilities associated with this model.

  • Abstract dynamics optimized for value prediction
  • No observation reconstruction
  • Multi-step lookahead planning
  • Bridges model-free and model-based RL

Use Cases

Representative applications attached to this model record.

Value-based planningAtari gamesAbstract decision-making

Strengths and Limitations

Balanced assessment surfaced in static HTML.

Strengths

  • No reconstruction loss needed
  • Focused on decision-relevant predictions
  • Efficient planning in abstract space
  • Theoretically clean approach

Limitations

  • Limited domain validation
  • Abstract space lacks interpretability
  • Superseded by Predictron and MuZero

Benchmarks

Published benchmark evidence attached to this model record.

BenchmarkMetricResultSource
AtariMean HNS 1.08 x baselineImproved over model-free baselinesSource

References and Citations

Primary references preserved in static HTML for citation extraction.

ReferenceLink
Oh et al., 2017. Value Prediction Network. NeurIPS 2017.Open source

Related Models

Nearby models linked from the current editorial record.

ModelCategoryWorld Model TypeIndex v1.1
PredictronModel-Based RLAbstract internal dynamics model43/100
MuZeroModel-Based RLAbstract learned dynamics + MCTS78/100

Direct Comparisons

Side-by-side comparisons already connected to this model.

ComparisonMatchupSummary
Predictron vs MuZeroPredictron vs MuZeroBoth learn abstract dynamics models for planning without requiring environment reconstruction, but Predictron was an early prototype while MuZero became the definitive realization of value-equivalent model learning.

Research Topics Referencing This Model

Connected research areas surfaced directly in static HTML.

TopicSummary
Model-Based Reinforcement LearningWhat model-based reinforcement learning is, how world models enable imagination-based planning, and why Dreamer, MuZero, PlaNet, and TD-MPC2 matter.

Frequently Asked Questions

FAQ answers rendered directly into static HTML for extractable responses.

How does VPN differ from the Predictron?

Both predict values in abstract space, but VPN explicitly learns state transitions and reward predictions along imagined trajectories, while the Predictron uses a single network with λ-weighted returns across depths.

Quick Answer

Short extractable summary preserved directly in static HTML.

  • Value Prediction Network (VPN) is a value-focused abstract dynamics developed by University of Michigan / Google Brain in 2017 for planning / games.
  • Use this page when you need a fast read on how Value Prediction Network (VPN) fits into the model-based rl landscape, then validate the details in the benchmarks, citations, and related pages.
  • A key strength surfaced in the editorial record is no reconstruction loss needed.

Editorial Trust Signals

Editorial provenance and refresh policy preserved directly in static HTML.

Published by world-models.io editorial board.

Lead editor Tyler D. - Technical editor, methodology and benchmark analysis.

This model page synthesizes primary papers, official model pages, benchmark evidence, and related world-models.io context into a reference resource.

Each editorial page is assembled from primary sources, normalized into extractable summaries, checked for factual drift, and reviewed before publication or major refreshes. Last reviewed: 2026-01-15.

Pages are refreshed when a new paper, benchmark, release, architecture update, or stronger primary source materially changes the answer a reader or AI system should retrieve.

Each page links back to relevant primary sources and keeps a stable canonical URL so readers can verify claims, trace context, and reference the most up-to-date version. See the editorial policy.

Primary sources onlyLast reviewed date visibleMethodology documentedSource links included

External Sources

Primary model and lab sources embedded in static HTML.

References

  1. [1] Oh et al., 2017. Value Prediction Network. NeurIPS 2017.