Awesome World Model Hub Papers · Datasets · Projects
← Back to papers

Latent Action World Models for Control with Unlabeled Trajectories

arXiv 25.12 2025 55.9 method

TLDR

Latent-action world models learn from both labeled and unlabeled trajectories, enabling efficient control with few action labels.

Reasoning

The paper introduces a novel latent-action representation to align action-conditioned and action-free data, showing strong results on simulated benchmarks. However, it lacks real-world validation and does not address scalability to complex environments.

Read-first score

Read-first score 55.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 44.

Recency 8%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Topical relevance 42%
62.9

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Methodology quality 25%
60

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=baseline,result

Reproducibility 25%
30

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 359.

Keyword Scores

world model
10
model-based reinforcement learning world model
9
world dynamics prediction
8
interactive world model
6
video world model
5
generative world model
4
world simulator
2

Deep Analysis

Innovations

  • Joint use of action-conditioned and action-free data via a shared latent action representation
  • Latent-action policy learned through offline RL, bridging offline RL and action-free training
  • Enables training on both passive and interactive data for more efficient world model learning

Methodology

The paper introduces a family of latent-action world models that learn a shared latent action representation from both action-conditioned and action-free data. This latent space aligns observed control signals with actions inferred from passive observations, allowing a single dynamics model to train on large-scale unlabeled trajectories with only a small set of action-labeled ones. The latent-action world model is then used to learn a latent-action policy via offline reinforcement learning.

Key Results

On the DeepMind Control Suite, the approach achieves strong performance while using about an order of magnitude fewer action-labeled samples than purely action-conditioned baselines.

Tags