Deep Reinforcement Learning from Self-Play in Imperfect-Information Games. (arXiv:1603.01121v2 [cs.LG] UPDATED)

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.

DONATE to arXiv: One hundred percent of your contribution will fund improvements and new initiatives to benefit arXiv's global scientific community. Please join the Simons Foundation and our generous member organizations and research labs in supporting arXiv. https://goo.gl/QIgRpr

from cs.AI updates on arXiv.org http://ift.tt/1QWDK7A
via IFTTT