Melioration learning is an empirically well-grounded model of reinforcement learning. By means of computer simulations, this paper derives predictions for several repeatedly played two-person games from this model. The results indicate a likely convergence to a pure Nash equilibrium of the game. If no pure equilibrium exists, the relative frequencies of choice may approach the predictions of the mixed Nash equilibrium. Yet in some games, no stable state is reached.
| Identifer | oai:union.ndltd.org:DRESDEN/oai:qucosa.de:bsz:15-qucosa-213943 |
| Date | 23 November 2016 |
| Creators | Zschache, Johannes |
| Contributors | Universität Leipzig, Fakultät für Sozialwissenschaften und Philosophie, Public Library of Science, |
| Publisher | Universitätsbibliothek Leipzig |
| Source Sets | Hochschulschriftenserver (HSSS) der SLUB Dresden |
| Language | English |
| Detected Language | English |
| Type | doc-type:article |
| Format | application/pdf |
| Source | PLoS ONE 11(11): e0166708 doi:10.1371/journal.pone.0166708 |
Page generated in 0.0019 seconds