Skip to content

wfishell/Imperfect_Information_Automata_Learning

Repository files navigation

Git clone remap repo into local project s.t. you can run code such as LLM teacher. Need an antrhopic API key, can send you mine or push a hidden version here, but don't think we should be doing it this way personally.

git clone https://github.com/eric-hsiung/REMAP.git

TODO

  1. Get preference querying working for Kuhn Poker with perfect information game working. Currently have an HOA and TLSF file for Kuhn poker. Can use dot_trace_generator.py to generate a lot of traces of games for data gen
  2. Need to figure out if REMAP training data intake works as I think it does.
  3. Once we get reward machine LLM working we can go onto step two of L* modification

About

Generating Deterministic Strategies for Complex Games

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors