Bayesian reinforcement learning in markovian and non-markovian tasks

Adnane Ez-Zizi, Simon Farrell, David Leslie

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

247 Downloads (Pure)

Abstract

We present a Bayesian reinforcement learning model with a working memory module which can solve some non-Markovian decision processes. The model is tested, and compared against SARSA (lambda), on a standard working-memory task from the psychology literature. Our method uses the Kalman temporal difference framework, And its extension to stochastic state transitions, to give posterior distributions over state-action values. This framework provides a natural mechanism for using reward information to update more than the current state-action pair, and thus negates the use of eligibility traces. Furthermore, the existence of full posterior distributions allows the use of Thompson sampling for action selection, which in turn removes the need to choose an appropriately parameterised action-selection method.
Original languageEnglish
Title of host publication2015 IEEE Symposium Series on Computational Intelligence
Subtitle of host publicationProceedings of a meeting held 7-10 December 2015, Cape Town, South Africa
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages579-586
Number of pages8
ISBN (Electronic)9781479975600
ISBN (Print)9781479975617
DOIs
Publication statusPublished - Apr 2016

Fingerprint Dive into the research topics of 'Bayesian reinforcement learning in markovian and non-markovian tasks'. Together they form a unique fingerprint.

Cite this