Limitations and Extensions of the WoLF-PHC Algorithm

Policy Hill Climbing (PHC) is a reinforcement learning algorithm that extends Q-learning to learn probabilistic policies for multi-agent games. WoLF-PHC extends PHC with the "win or learn fast" principle. A proof that PHC will diverge in self-play when playing Shapley's game is given, and WoLF-PHC is shown empirically to diverge as well. Various WoLF-PHC based modifications were created, evaluated, and compared in an attempt to obtain convergence to the single shot Nash equilibrium when playing Shapley's game in self-play without using more information than WoLF-PHC uses. Partial Commitment WoLF-PHC (PCWoLF-PHC), which performs best on Shapley's game, is tested on other matrix games and shown to produce satisfactory results.

Name thesis:degree_name

MS

Grantor dc:publisher

Brigham Young University - Provo

Author dc:creator

• Cook, Philip R.

• Matrix Games
• Multi-agent Systems
• Nash equilibrium
• convergence
• reinforcement learning
• machine learning
• algorithm
• Computer Sciences

Language dc:language

English

Repository record dc:identifier

https://scholarsarchive.byu.edu/etd/1222

OAI identifier oai:identifier

oai:scholarsarchive.byu.edu:etd-2221