Learning within a Markovian Environment

Javier Rivas ()

No ECO2008/13, Economics Working Papers from European University Institute

Abstract: We investigate learning in a setting where each period a population has to choose between two actions and the payoff of 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 of each action today and the payoff of each action in the past. We show that when players observe realized and foregone payoffs, a suboptimal mixed strategy is selected. On the other hand, when players only observe realized payoffs, 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 payoffs and to learn as if only realized payoffs were observed.

Keywords: Adaptive Learning; Markov Chains; Non-stationarity; Reinforcement Learning (search for similar items in EconPapers)
JEL-codes: C73 (search for similar items in EconPapers)
New Economics Papers: this item is included in nep-cba, nep-cbe, nep-evo and nep-gth
Date: Written 2008
View list of references

Downloads: (external link)
http://cadmus.iue.it/dspace/bitstream/1814/8084/1/ECO-2008-13.pdf main text

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Access Statistics for this paper

More papers in Economics Working Papers from European University Institute
Address: Badia Fiesolana, Via dei Roccettini, 9, 50016 San Domenico di Fiesole (FI) Italy
Contact information at EDIRC.
Series data maintained by Marcia Gastaldo ().