ParamThakkar123/simulusion

A platform for reproducible world model research and evaluation

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

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

Training models inside world models

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Puffing up reinforcement learning

Mastering Diverse Domains through World Models