ikostrikov / pytorch-a2c-ppo-acktr-gail

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
MIT License
3.53k stars 832 forks source link

replace baselines dependencies #254

Closed vwxyzjn closed 3 years ago

vwxyzjn commented 3 years ago

openai/baselines has tensorflow and mujoco dependencies by default. Tensorflow installation is not necessary for scripts in this repo and mujoco is not very friendly to build. It might be quite desirable to remove these dependencies by using stable_baselines3 as done in this PR.

ikostrikov commented 3 years ago

Hi @vwxyzjn,

Thanks for doing this!

I'm merging the PR.

ikostrikov commented 3 years ago

@vwxyzjn could you also update the README and requirements.txt?

vwxyzjn commented 3 years ago

Yeah would be happy to.