search

Toni-SM / skrl

Modular reinforcement learning library (on PyTorch and JAX) with support for NVIDIA Isaac Gym, Omniverse Isaac Gym and Isaac Lab
https://skrl.readthedocs.io/
MIT License
443 stars 43 forks source link

I notice that MAPPO is supportted in 0.11.0 #76

Closed 394262597 closed 1 year ago

394262597 commented 1 year ago

Hi, I notice that MAPPO is supportted in 0.11.0, and I'm really eager for using MAPPO algorithm in NVIDIA Isaac Sim, but this work may have not shown for us. Could you please tell me what time may I use MAPPO? In addition, If I create MAPPO class in skrl.agents.torch by myself, is it possible to work? Very thanks!

Toni-SM commented 1 year ago

Hi @394262597

Multi-agent reinforcement learning is one of the feature I am working for the next (mayor) release.

However, you can try it with skrl by changing to or cloning the multi-agent branch. Available algorithms are MAPPO and IPPO, at the moment.

In the next link you can find more information and an example for the Bi-Dexhands ShadowHand Over environment (created on top of Isaac Gym preview 4).

https://github.com/Toni-SM/skrl/discussions/51#discussioncomment-5277749

It should be straightforward to adapt for MAPPO and Omniverse Isaac Gym