[rllib] multi-task RL with Rllib

ray-project / ray

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

https://ray.io

Apache License 2.0

33.76k stars 5.74k forks source link

[rllib] multi-task RL with Rllib #15517

Closed AprilXiaoyanLiu closed 3 years ago

AprilXiaoyanLiu commented 3 years ago

Hello,

I'm trying to implement one simple multi-task RL (universal functional approximator) where the input is current state and specific task and generated goal-conditioned reward.

I tried to search if there is any example of using RLlib to perform this, but what I found is only to customize multi-agent for this scenario. Techinically this is not multi-agent because it's the same agent with the shared policy (just the input is different).

Is there any recommendation of how to use RLLib for this?

mvindiola1 commented 3 years ago

Hi @AprilXiaoyanLiu,

I think it will be easier to make suggestions with more concrete information about the environment an policies if you have them available.

stale[bot] commented 3 years ago

Hi, I'm a bot from the Ray team :)

To help human contributors to focus on more relevant issues, I will automatically add the stale label to issues that have had no activity for more than 4 months.

If there is no further activity in the 14 days, the issue will be closed!

If you'd like to keep the issue open, just leave any comment, and the stale label will be removed!
If you'd like to get more attention to the issue, please tag one of Ray's contributors.

You can always ask for help on our discussion forum or Ray's public slack channel.

stale[bot] commented 3 years ago

Hi again! The issue will be closed because there has been no more activity in the 14 days since the last message.

Please feel free to reopen or open a new issue if you'd still like it to be addressed.

Again, you can always ask for help on our discussion forum or Ray's public slack channel.

Thanks again for opening the issue!