Deep Reinforcement Learning from Self-Play in Imperfect-Information Games

Code

• github.com/deepmind/open_spiel
  none★ 5,095
• github.com/EricSteinberger/DREAM
  none★ 120
• github.com/quantumiracle/mars
  pytorch★ 49
• github.com/jsanderink/tue
  pytorch★ 0
• github.com/heidekrueger/bnelearn
  pytorch★ 0
• github.com/TinkeringCode/Neural-Fictitous-Self-Play
  pytorch★ 0
• github.com/IAARhub/TrucoAnalytics
  none★ 0

Abstract

Many real-world applications can be described as large-scale games of imperfect information. To deal with these challenging domains, prior work has focused on computing Nash equilibria in a handcrafted abstraction of the domain. In this paper we introduce the first scalable end-to-end approach to learning approximate Nash equilibria without prior domain knowledge. Our method combines fictitious self-play with deep reinforcement learning. When applied to Leduc poker, Neural Fictitious Self-Play (NFSP) approached a Nash equilibrium, whereas common reinforcement learning methods diverged. In Limit Texas Holdem, a poker game of real-world scale, NFSP learnt a strategy that approached the performance of state-of-the-art, superhuman algorithms based on significant domain expertise.

Tasks

Reproductions