English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Preprint

Exploration With a Finite Brain

MPS-Authors
/persons/resource/persons256660

Binz,  M
Research Group Computational Principles of Intelligence, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons139782

Schulz,  E
Research Group Computational Principles of Intelligence, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource
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

Binz, M., & Schulz, E. (submitted). Exploration With a Finite Brain.


Cite as: http://hdl.handle.net/21.11116/0000-0009-EEC2-0
Abstract
Equipping artificial agents with useful exploration mechanisms remains a challenge to this day. Humans, on the other hand, seem to manage the trade-off between exploration and exploitation effortlessly. In the present article, we put forward the hypothesis that they accomplish this by making optimal use of limited computational resources. We study this hypothesis by meta-learning reinforcement learning algorithms that sacrifice performance for a shorter description length. The emerging class of models captures human exploration behavior better than previously considered approaches, such as Boltzmann exploration, upper confidence bound algorithms, and Thompson sampling. We additionally demonstrate that changes in description length produce the intended effects: reducing description length captures the behavior of brain-lesioned patients while increasing it echoes cognitive development during adolescence.