python interactive_ppo_gym.py --env-name Quadraticm6k2 --seed 1 --learning-rate 3e-3 --max-iter-num 10000 --logger-name log --number-subspace 1 --noise-mult 3
The Actor part of the code is forked from https://github.com/Khrylx/PyTorch-RL
The Critic part of the code is forked from https://github.com/ghliu/pytorch-ddpg