AlphaNPI
PublicAdapting the AlphaZero algorithm to remove the need of execution traces to train NPI.
deep-learningdeep-reinforcement-learningmachine-learningneural-networksneural-program-synthesisneural-programmer-interpreterreinforcement-learning
Creat:2019-05-27T18:06:28
Update:2024-12-19T21:53:37
79
Stars
0
Stars Increase