Reproduce “Using Transformers for Teaching and Learning via Symbolic Distillation of Neural A-life Agents” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Shuwei Wang, Vadim Bulitko, Matthew R. G. Brown, Michael Youngblood, Ramon Lawrence, Roscoe Smith, Shinichi Nakagawa, William Yeoh
The authors train a transformer to translate percept-action examples from artificial-life agents into symbolic policies that approximate neural controllers. Training uses synthetic policies sampled from a purpose-built language, rather than examples from evolved agents. On 243 filtered agents in one testbed, transformer inference takes 0.63 or 4.08 seconds on average and exceeds tested genetic-algorithm methods in average held-out accuracy.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.