Add the GRPO-on-Substrate example: a real RL loop with actors as the reward executor - #101

Add the GRPO-on-Substrate example: a real RL loop with actors as the reward executor#101

Vicente Ferrara (vicentefb) wants to merge 4 commits into

agent-substrate:mainagent-substrate/env:mainfrom

vicentefb:examples/grpo-harnessvicentefb/env:examples/grpo-harnessCopy head branch name to clipboard