AI Coding with CodeRL: Toward Mastering Program Synthesis with Deep RL

The TL;DR is that this appears to beat both OpenAI Codex (12 billion params) and DeepMind's AlphaCode (1 billion params), despite having only 770M parameters.

There is also a paper: https://arxiv.org/abs/2207.01780

And the code is available: https://github.com/salesforce/CodeRL