HN Explorer

End-to-End RL Post-Training

4 points by sarthakaggarwal ↗ HN
https://maxreward.vercel.app/

Reinforcement Learning is fun, but building the RL pipeline is not fun. We bring the fun back in RL.

3 comments

[ 3.2 ms ] story [ 14.4 ms ] thread
navyanshmahla
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!