X · @cwolferesearch
· X / Twitter
RT Sergio Paniego: completely agree with this take that the hardest part of agentic RL is managing and scaling the environments, not the algorithm (an…
RT Sergio Paniegocompletely agree with this take that the hardest part of agentic RL is managing and scaling the environments, not the algorithm (and why I find it super interesting to be working on this since it touches so many areas at once)got both the agentic RL and eval guides on the reading list 🤓> https://camero