A parallel network that learns to play backgammon
From MaRDI portal
Publication:1124371
DOI10.1016/0004-3702(89)90017-9zbMath0678.68087MaRDI QIDQ1124371
Publication date: 1989
Published in: Artificial Intelligence (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/0004-3702(89)90017-9
68T05: Learning and adaptive systems in artificial intelligence
Related Items
Nonparametric graded data processing with back-error propagation networks, Practical issues in temporal difference learning