eloialonso/diamond

Mastering Diverse Domains through World Models

Implementation of R2-Dreamer.

Mastering Atari with Discrete World Models

Implementation of Danijar's latest iteration for his Dreamer line of work

Training models inside world models

Combining Diffusion Models with PPO to Improve Sample Efficiency and Exploration in Reinforcement Learning

A modular PyTorch library designed for learning, training, and deploying world models across various environments.

official implementation of QVPO

Code, results and checkpoints for the paper "Silent Pipeline Defects in World-Model RL: A Dreamer 4 Case Study": a PyTorch reimplementation of Dreamer 4, two silent defects that passed 12 checks, and three cheap checks that catch them