Matthew West

arxiv2markdown

arxiv2markdown ← drag this bookmarklet into your browser shortcuts bar, then click it when on an arXiv abstract page

Example text follows for testing. Click the arxiv2markdown link above to run it on this page.

Drag the arxiv2markdown link above to your shortcuts bar to use it on real arXiv abstract pages.


Computer Science > Artificial Intelligence

Title: Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Abstract: The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcrafted evaluation functions that have been refined by human experts over several decades. In contrast, the AlphaGo Zero program recently achieved superhuman performance in the game of Go, by tabula rasa reinforcement learning from games of self-play. In this paper, we generalise this approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance in many challenging domains. Starting from random play, and given no domain knowledge except the game rules, AlphaZero achieved within 24 hours a superhuman level of play in the games of chess and shogi (Japanese chess) as well as Go, and convincingly defeated a world-champion program in each case.
Subjects: Artificial Intelligence (cs.AI); Learning (cs.LG)
Cite as: arXiv:1712.01815 [cs.AI]
  (or arXiv:1712.01815v1 [cs.AI] for this version)

Submission history

From: David Silver [view email]
[v1] Tue, 5 Dec 2017 18:45:38 GMT (272kb,D)