sizzle0121 / Mujoco-Hopper

Mujoco Hopper agent with DDPG

Mujoco-Hopper

Mujoco Hopper agent with Deep Deterministic Policy Gradient(DDPG)

Build Requirement

Python 3.5
Pytorch 0.4.1
CUDA is depend on GPU
Simply run with python hopper.py

Result

Training Return
Red line is the average return accumulating throughout the training sequence