mathieu-calvo/Incomplete-Info-Problem
Incomplete Information Problem using Reinforcement Learning and Opponent Modelling. A heads-up Limit Texas Hold'em bot trained with Deep CFR and fine-tuned with PPO self-play, plus a Streamlit Cloud app where humans play the bot and contribute hands to a nightly retraining pipeline
GitHub repository with 7 stars and 0 forks.
Language: Python