Reward for partial or complete successful solution to a programming problem

Glavin001 / PeakProgrammer

Mastering coding precision with fine-tuned reinforcement learning

MIT License

0 stars 0 forks source link

Open Glavin001 opened 1 year ago

Glavin001 commented 1 year ago

Given a problem with a known behaviour/suite of tests
When the tests are performed
Then the % score is provided as a reward to the model