Replies: 1 comment 1 reply
-
|
Combining MPC and RL indeed seems like an interesting avenue to explore, although I'm not sure how it'll relate to GRPO specifically. I've dabbled previously with MPPI + offline RL (MBOP and POIR). I'm not really familiar with approaches that do this for online RL, hopefully someone else can chime in. |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
https://superb-makemake-3a4.notion.site/group-relative-policy-optimization-GRPO-18c41736f0fd806eb39dc35031758885 |
Beta Was this translation helpful? Give feedback.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Recently,I am reading some papers and articles about grpo, a different reinforcement learning algorithm. It looks like someone that integrate mppi and rl. Does it a good idea for robotics?
Beta Was this translation helpful? Give feedback.
All reactions