Learning within a Markovian Environment

DSpace/Manakin Repository

Show simple item record

dc.contributor.author RIVAS, Javier
dc.date.accessioned 2008-02-13T13:21:14Z
dc.date.available 2008-02-13T13:21:14Z
dc.date.issued 2008
dc.identifier.issn 1725-6704
dc.identifier.uri http://hdl.handle.net/1814/8084
dc.description.abstract We investigate learning in a setting where each period a population has to choose between two actions and the payoff each action is unknown by the players. The population learns according to reinforcement and the environment is non-stationary, meaning that there is correlation between the payoff each action today and the payoff each action in the past. We show that when players observe realized and foregone payoff, a suboptimal mixed strategy is selected. On the other hand, when players only observe realized payoff, a unique action, which is optimal if actions perform different enough, is selected in the long run. When looking for efficient reinforcement learning rules, we find that it is optimal to disregard the information from foregone payoff and to learn as if only realized payoff were observed. population learns according to reinforcement and the environment is non-stationary, meaning that there is correlation between the payo of each action today and the payo of each action in the past. We show that when players observe realized and foregone payo s, a suboptimal mixed strategy is selected. On the other hand, when players only observe realized payo s, a unique action, which is optimal if actions perform di erent enough, is selected in the long run. When looking for e cient reinforcement learning rules, we nd that it is optimal to disregard the information from foregone payo s and to learn as if only realized payo s were observed. en
dc.language.iso en en
dc.publisher European University Institute
dc.relation.ispartofseries EUI ECO en
dc.relation.ispartofseries 2008/13 en
dc.subject C73 en
dc.subject Adaptive Learning en
dc.subject Markov Chains, en
dc.subject Non-stationarity en
dc.subject Reinforcement Learning en
dc.title Learning within a Markovian Environment en
dc.type Working Paper en
dc.neeo.contributor RIVAS|Javier|aut|
eui.subscribe.skip true


Files in this item

This item appears in the following Collection(s)

Show simple item record