Co-evolution in the successful learning of backgommon strategy

DOI10.1023/A:1007417214905zbMath0913.90289OpenAlexW2112180705MaRDI QIDQ1275354

Alan D. Blair, Jordan B. Pollack

Publication date: 17 January 1999

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1023/a:1007417214905

zbMATH Keywords

feedforward neural networktemporal difference learningreinforcementself-learningbackgammon evaluation function

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Probabilistic games; gambling (91A60)

Related Items (5)

The performance profile: a multi-criteria performance evaluation method for test-based problems ⋮ Backgammon is hard ⋮ A survey on optimization metaheuristics ⋮ Evolving small-board Go players using coevolutionary temporal difference learning with archives ⋮ Programming backgammon using self-teaching neural nets

This page was built for publication: Co-evolution in the successful learning of backgommon strategy