search

Khrylx / PyTorch-RL

PyTorch implementation of Deep Reinforcement Learning: Policy Gradient methods (TRPO, PPO, A2C) and Generative Adversarial Imitation Learning (GAIL). Fast Fisher vector product TRPO.
MIT License
1.09k stars 186 forks source link

Various questions? #26

Open lviano opened 3 years ago

lviano commented 3 years ago

Hi,

Thanks a lot for this extremely useful implementation.

I wanted just to ask what is the ZFilter class, is it used to standardize the observed state according to the running mean and std of the observed states?

In addition, in the GAIL paper, they consider in the TRPO update a step in the direction of the gradient of the entropy. Is it considered here? I am not managing to find it in the code.

Thank you in advance.

Luca

MachengShen commented 2 years ago

Hi, I have the same question. What is the running state in your GAIL code? Is it some trick that helps the learning? I noticed that when replaced with a newly-initiated running state instead of the one load from the pickle file, the learned policy becomes much worse. Would appreciate it if you can clarify what role this running state plays.