rickstaa / stable-learning-control

A framework for training theoretically stable (and robust) Reinforcement Learning control algorithms.
https://rickstaa.dev/stable-learning-control
MIT License
6 stars 1 forks source link

Add SAC/LAC mpi support #270

Open rickstaa opened 1 year ago

rickstaa commented 1 year ago

Is your feature request related to a problem? Please describe.

Currently, none of the algorithms in the SLC package have MPI support.

Describe the solution you'd like

In the future, we can add MPI support to the SAC and LAC Pytorch algorithms. All the components needed for the Pytorch version are already present, but they need to be added to the algorithms (see https://github.com/openai/spinningup/blob/master/spinup/algos/pytorch/ppo/ppo.py for an example of how to do this).

Describe alternatives you've considered

No response

Additional context

No response

rickstaa commented 1 year ago

Not on the immediate roadmap. Feel free to comment below if you want to take this feature on in the future 👍🏻.