Comparison to other PyTorch RL libraries

[janacht]

There is a large variety of reinforcement libraries using PyTorch, just to name a few

• https://github.com/ray-project/ray
• https://github.com/DLR-RM/stable-baselines3
• https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail
• https://github.com/astooke/rlpyt
• https://github.com/thu-ml/tianshou
• https://github.com/p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch

For potential future users, it could be a big benefit to highlight the advantages / differences in design choices / performance differences to the above libraries in the README, similar to https://github.com/thu-ml/tianshou#fast-speed.

[Sharad24]

Hi @janacht

Thanks for pointing this out. Yes, we do need to add more details to the Readme.

[sampreet-arthi]

Tracking in #382