Guojian Zhan's repositories
Pontryagin-Differentiable-Programming
A unified end-to-end learning and control framework that is able to learn a (neural) control objective function, dynamics equation, control policy, or/and optimal trajectory in a control system.
CAGrad
Official PyTorch Implementation for Conflict-Averse Gradient Descent (CAGrad)
D4RL
A collection of reference environments for offline reinforcement learning
GOPS
General Optimal control Problem Solver (GOPS), an easy-to-use PyTorch reinforcement learning solver package for industrial control.
mjrl
Reinforcement learning algorithms for MuJoCo tasks
PRDC
Author's PyTorch implementation of ICML'23 paper "Policy Regularization with Dataset Constraint for Offline Reinforcement Learning" for D4RL gym and AntMaze tasks.