instadeepai / AlphaNPI Star 79 Code Issues Pull requests Adapting the AlphaZero algorithm to remove the need of execution traces to train NPI. machine-learning reinforcement-learning deep-learning deep-reinforcement-learning neural-networks neural-program-synthesis neural-programmer-interpreter Updated Oct 3, 2023 Python
geektoni / AlphaNPI2 Star 4 Code Issues Pull requests Improved version of the AlphaNPI model (https://arxiv.org/abs/1905.12941) pytorch deep-networks neural-program-synthesis Updated Oct 3, 2023 Python