A curated collection of Reinforcement Learning (RL) algorithms implemented from scratch along with applications and experiments in different domains. The goal of this repository is to provide clear, well-documented implementations that are both educational and practical.
-
Implementations of classical and modern RL algorithms in Mujoco with Pytorch and JAX
-
Applications to control, robotics, and simulation environments
-
Modular code for easy experimentation
-
Clean documentation and reproducible results
Prajwal Thakur