mlprogram

mlprogram copied to clipboard

HiroakiMikami

I should use a reliable library for reinforcement learning because RL is a complex and error-prone method. Now I plan to use [PFRL](https://github.com/pfnet/pfrl).

HiroakiMikami

* [ ] Write an initial implementation * [ ] Get the result similar to the paper

HiroakiMikami

HiroakiMikami

* [ ] Copy code from [my another repository](https://github.com/HiroakiMikami/deep-coder) and replace chainer with pytorch * [ ] Reproduce the result similar to the paper

HiroakiMikami

Add Write, Execute, Assess: Program Synthesis with a REPL

1

* [x] Write initial implementation * [ ] Make RL training stable * [ ] Reproduce the result similar to the paper

HiroakiMikami

Some vocabs in the ActionSequenceEncoder are not used. Special rules such as `None -> Root` and node types such as `Root` and `None` should be removed from the encoder.

HiroakiMikami

HiroakiMikami

Bumps [torch](https://github.com/pytorch/pytorch) from 1.8.0 to 2.2.0. Release notes Sourced from torch's releases. PyTorch 2.2: FlashAttention-v2, AOTInductor PyTorch 2.2 Release Notes Highlights Backwards Incompatible Changes Deprecations New Features Improvements Bug fixes...

dependabot[bot]