Evolving small-board Go players using coevolutionary temporal difference learning with archives

DOI10.2478/V10006-011-0057-3zbMath1286.91034OpenAlexW2165119088MaRDI QIDQ5403427

Krzysztof Krawiec, Wojciech Jaśkowski, Marcin Szubert

Publication date: 26 March 2014

Published in: International Journal of Applied Mathematics and Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.2478/v10006-011-0057-3

zbMATH Keywords

coevolutiongamestemporal difference learningexploration vs. exploitationsmall-board go

Mathematics Subject Classification ID

Rationality and learning in game theory (91A26) Combinatorial games (91A46) Experimental studies (91A90)

Related Items (3)

The performance profile: a multi-criteria performance evaluation method for test-based problems ⋮ Epoch-incremental reinforcement learning algorithms ⋮ Customized crossover in evolutionary sets of safe ship trajectories

Uses Software

• Genocop
• ECJ

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Co-evolution in the successful learning of backgommon strategy
• EMERGENCE OF COMPLEX STRATEGIES IN THE EVOLUTION OF CHESS ENDGAME PLAYERS
• Computer Go: An AI oriented survey

This page was built for publication: Evolving small-board Go players using coevolutionary temporal difference learning with archives