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

PlaNet

PlaNet (Deep Planning Network) introduced the RSSM architecture and demonstrated that model-based RL agents can learn latent dynamics and plan from image observations.

robotics model-based-rl simulation embodied-ai

Key Attributes

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

AttributeValue
ModelPlaNet
Lab / OrganizationDeepMind
CategoryModel-Based RL
SubtypeLatent Dynamics Model
World Model TypeLatent space planning model
Primary DomainContinuous control
ArchitectureRSSM with deterministic and stochastic paths
ModalityVisual
Training MethodVariational inference for latent dynamics learning
Statusfoundational
Year2019
Performance Index57/100 (high confidence, v1.1)

About PlaNet

Main editorial body preserved directly in static HTML.

PlaNet learns a latent dynamics model from image observations and plans directly in latent space using model-predictive control (MPC). It introduced the RSSM architecture and demonstrated that model-based approaches could match model-free methods while being dramatically more sample efficient.

PlaNet is a latent space planning model developed by Google in 2019 for continuous control.

Editorial Snapshot

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

SignalValue
DefinitionPlaNet is a latent space planning model developed by Google in 2019 for continuous control.
Short DescriptionDeep Planning Network: learns environment dynamics in latent space for image-based control without a policy network.
Benchmark Rows1
FAQ Entries1
Related Models3
Related Guides4
Related Research Topics2
Last Updated2026-02-05

Notable Features

Key capabilities associated with this model.

  • Introduced the RSSM architecture
  • Planning in latent space via CEM
  • No policy network required
  • Foundation for entire Dreamer family

Use Cases

Representative applications attached to this model record.

Continuous control from pixelsRobotics simulationSample-efficient RL

Strengths and Limitations

Balanced assessment surfaced in static HTML.

Strengths

  • Sample efficient
  • No policy network needed
  • Latent space planning
  • Foundational architecture

Limitations

  • Limited to short planning horizons
  • MPC computational cost
  • Superseded by Dreamer family

Benchmarks

Published benchmark evidence attached to this model record.

BenchmarkMetricResultSource
DMControl SuiteSample Efficiency 10 x more efficientCompetitive at 10x less dataSource

References and Citations

Primary references preserved in static HTML for citation extraction.

ReferenceLink
Hafner et al., 2019. Learning Latent Dynamics for Planning from Pixels. ICML 2019.Open source

Related Models

Nearby models linked from the current editorial record.

ModelCategoryWorld Model TypeIndex v1.1
DreamerV3Model-Based RLImagination-based dynamics model88/100
RSSMLatent DynamicsCore dynamics architecture64/100
DreamerV2Model-Based RLImagination-based dynamics model72/100

Direct Comparisons

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

ComparisonMatchupSummary
DreamerV3 vs PlaNetDreamerV3 vs PlaNetDreamerV3 represents the evolution of PlaNet's core ideas. Both use the RSSM architecture, but DreamerV3 adds discrete representations, symlog predictions, and fixed hyperparameters to achieve state-of-the-art performance across diverse domains.
DreamerV2 vs PlaNetDreamerV2 vs PlaNetBoth use the RSSM architecture for latent dynamics, but DreamerV2 introduced discrete representations that dramatically improved performance. PlaNet pioneered the approach; DreamerV2 perfected it for Atari-scale environments.
DreamerV3 vs TD-MPC2DreamerV3 vs TD-MPC2Two leading model-based RL agents with different philosophies: DreamerV3 uses imagination-based actor-critic learning, while TD-MPC2 combines temporal-difference learning with model-predictive control for multi-task mastery.
Ha & Schmidhuber World Model vs DreamerV3Ha & Schmidhuber World Model vs DreamerV3The original 2018 'World Models' paper vs. the current state-of-the-art: how five years of research transformed a foundational concept into a domain-general world model agent.
DreamerV2 vs DreamerV3DreamerV2 vs DreamerV3The Dreamer lineage's two most impactful iterations: DreamerV2 achieved human-level Atari with discrete representations, while DreamerV3 eliminated hyperparameter tuning entirely with symlog predictions.

Guides Referencing This Model

Crawler-readable guide links tied to this model.

GuideSummary
World Models for BeginnersA comprehensive introduction to AI world models: what they are, how they work, and why they matter for the future of robotics, reinforcement learning, and embodied AI.
Understanding the RSSM ArchitectureA technical guide to the Recurrent State-Space Model: the foundational architecture behind PlaNet and the Dreamer family of world models.
Building World Models: A Practical GuideA practical guide to implementing world models: from choosing architectures and training setups to debugging dynamics learning and policy optimization.
How to Read World Models PapersA practical reading path through world-model research, from foundational concepts to latent dynamics, planning, simulators, and self-supervised approaches.

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.
World Models: A Comprehensive SurveyA survey of AI world models covering taxonomy, leading architectures, landmark systems, open challenges, and future research directions.

Frequently Asked Questions

FAQ answers rendered directly into static HTML for extractable responses.

What is the RSSM?

The Recurrent State-Space Model combines deterministic recurrent states with stochastic latent variables to capture both predictable dynamics and uncertainty.

Quick Answer

Short extractable summary preserved directly in static HTML.

  • PlaNet is a latent space planning model developed by Google in 2019 for continuous control.
  • Use this page when you need a fast read on how PlaNet 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 sample efficient.

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: 2026-02-05.

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] Hafner et al., 2019. Learning Latent Dynamics for Planning from Pixels. ICML 2019.