Reinforcement Learning and the Bayesian Control Rule

Ortega, PA; Braun, DA; Godsill, S; Schmidhuber,; J.,; Thórisson, K.R.; Looks, M.

doi:10.1007/978-3-642-22887-2_30

Item

ITEM ACTIONSEXPORT

Add to Basket

Please note that a newer version of this item is available:
https://pure.mpg.de/pubman/item/item_1788102_2

DetailsSummary

Released

Conference Paper

Reinforcement Learning and the Bayesian Control Rule

MPS-Authors

/persons/resource/persons84121

Ortega, PA
Research Group Sensorimotor Learning and Decision-Making, Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons83827

Braun, DA
Research Group Sensorimotor Learning and Decision-Making, Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource

No external resources are shared

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Ortega, P., Braun, D., & Godsill, S. (2011). Reinforcement Learning and the Bayesian Control Rule. In Artificial General Intelligence (pp. 281-285). Berlin, Germany: Springer.

Cite as: https://hdl.handle.net/11858/00-001M-0000-0013-BADC-6

Abstract

We present an actor-critic scheme for reinforcement learning in complex domains. The main contribution is to show that planning and I/O dynamics can be separated such that an intractable planning problem reduces to a simple multi-armed bandit problem, where each lever stands for a potentially arbitrarily complex policy. Furthermore, we use the Bayesian control rule to construct an adaptive bandit player that is universal with respect to a given class of optimal bandit players, thus indirectly constructing an adaptive agent that is universal with respect to a given class of policies.