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

PWM: Policy Learning with Large World Models

arXiv 24.7 2024 64.4 method

TLDR

PWM uses well-regularized world models to enable efficient first-order policy optimization, achieving strong multi-task continuous control results.

Reasoning

The paper presents a novel insight that regularization smooths world model landscapes, enabling gradient-based policy extraction. Strengths include strong empirical results across many tasks and fast optimization. Weaknesses include reliance on offline pre-training and lack of explicit real-world validation.

Read-first score

Read-first score 64.4, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 46.

Recency 8%
75.1

Uses a gentle age decay so recent papers surface without erasing older foundations. 2024

Reproducibility 25%
73

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=True; dataset=False; markers=code

Topical relevance 42%
65.7

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%
50

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

Field roles

Reproducibility anchor

Rank sensitivity

Stability: volatile; rank range: 164.

Keyword Scores

world model
10
model-based reinforcement learning world model
10
world dynamics prediction
9
world simulator
7
generative world model
6
interactive world model
3
video world model
1

Deep Analysis

Innovations

  • Reveals that well-regularized world models generate smoother optimization landscapes than actual dynamics, enabling effective first-order optimization
  • Introduces PWM, a model-based RL algorithm that pre-trains a world model on offline data and extracts policies via first-order optimization in under 10 minutes per task
  • Scales to 80-task settings with up to 27% higher rewards than existing baselines without relying on costly online planning

Methodology

PWM is a model-based RL algorithm for continuous control. It first pre-trains a world model on offline data, then extracts policies from the learned model using first-order (gradient-based) optimization. The approach is evaluated on tasks with up to 152 action dimensions and in an 80-task multi-task setting, comparing against methods using ground-truth dynamics and other baselines.

Key Results

PWM solves tasks with up to 152 action dimensions and outperforms methods that use ground-truth dynamics. In an 80-task setting, it achieves up to 27% higher rewards than existing baselines without online planning.

Tags