https://maxreward.vercel.app/
Reinforcement Learning is fun, but building the RL pipeline is not fun. We bring the fun back in RL.
End-to-End RL Post-Training
1–4 of 4 posts
Re: End-to-End RL Post-Training
#2[dead]
Re: End-to-End RL Post-Training
#3Pretty good for the devs I feel. Takes up a lot of my inertia to go away from prompt engineering to something that actually works!
Re: End-to-End RL Post-Training
#4Amazing work!