zapper-95 / Coup-RL

Models trained to play the card game Coup
0 stars 0 forks source link

Experiment - Compare to Starcheus' algorithms #32

Closed zapper-95 closed 5 months ago

zapper-95 commented 6 months ago

The only other published work applying RL to coup, has the code publicly available: https://github.com/BStarcheus/open_spiel_coup

The best performing agent was NFSP-1. I should investigate if I can train a PPO agent that can beat it.