World Models

Generative World Modelling for Humanoids: 1X World Model Challenge Technical Report

Technical report detailing our method that won the 1X World Model Challenge 2025.

1X World Model Challenge

Introduction World models equip agents (e.g., humanoid robots) with internal simulators of their environments. By “imagining” the consequences of their actions, agents can plan, …

Efficient Reinforcement Learning by Guiding Generalist World Models with Non-Curated Data

Discrete Codebook World Models for Continuous Control

Aidan Scannell

• 28 Jan, 2025 • 1 min read

Read more

Discrete Codebook World Models

In reinforcement learning (RL), world models serve as internal simulators, enabling agents to predict environment dynamics and future outcomes in order to make informed decisions. …