PyTorch implementation of Constrained Policy Optimization

RARE-3D: Reinforcement Learning–based Adaptive Path Selection for Efficient Point-Cloud Restoration

Implmentation of Trust Region Policy Optimization (TRPO) from scratch. Tested on standard mujoco-based gymnasium environments. Extended to a harder task of Quadrupedal Locomotion with the help of gait priors.

A repository for easy understanding of codes in Deep Reinforcement Learning

The pytorch implemetation of trpo