We propose a new classification for multi-agent learning algorithms, with each league of players characterized by both their possible strategies and possible beliefs. Using this classification, we review the optimality of existing algorithms and discuss some insights that can be gained. We propose an incremental improvement to the existing algorithms that seems to achieve average payoffs that are at least the Nash equilibrium payoffs in the long-run against fair opponents. / Singapore-MIT Alliance (SMA)
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/3688 |
| Date | 01 1900 |
| Creators | Chang, Yu-Han, Kaelbling, Leslie P. |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Type | Article |
| Format | 114175 bytes, application/pdf |
| Relation | Computer Science (CS); |
Page generated in 0.002 seconds