Repository
dreamer · danijar
Dreamer implementation for learning control behaviors with latent world models.
Motion planning & control
Research & learning / Open source
A curated collection of papers, explainers, and resources on World Action Models for embodied AI
A curated collection of papers, explainers, and resources on World Action Models for embodied AI
Use the source to explore robotics concepts, examples and references. Source material may be historical; check the applicable version and context.
Code licenses do not automatically cover model weights, datasets or hardware designs. Unrecorded license details require confirmation with the publisher.
Repository
Dreamer implementation for learning control behaviors with latent world models.
Motion planning & control
Repository
Repository for our papers: Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics and Uncertainty-Aware Robotic World Model Makes Offline Model-Based…
World models
Repository
DayDreamer provides world-model methods for physical robot learning.
World models
Repository
Repository
Unfied World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
Robot demonstrations
Repository
Video-Action Models for Generalizable Robot Control Beyond VLAs
Robot learning frameworks