End-to-End RL Post-Training
https://maxreward.vercel.app/
Reinforcement Learning is fun, but building the RL pipeline is not fun. We bring the fun back in RL.
(
2 comments
| 4 points
| on HN
)
Re:End-to-End RL Post-Training
by navyanshmahla on Saturday May 17, 2025 @09:39PM
(#44018320)
Pretty good for the devs I feel. Takes up a lot of my inertia to go away from prompt engineering to something that actually works!
[ Parent
| on HN ]
Re:End-to-End RL Post-Training
by aryansonwatikar on Saturday May 17, 2025 @11:13PM
(#44018739)
Amazing work!
[ Parent
| on HN ]