Train the agent slides
sergiopaniego · Kit
A browser slide deck on how AI agents are trained with TRL and OpenEnv, from SFT on agent traces to GRPO and RL in environments. Made for developers learning a…
New
AI skills for learning and teaching
Prompts that quiz you on a subject or explain a hard idea in plain words.
Categories and filters
No listing has every word of “gspo”. Showing what matches “grpo” instead.