Reward-dependent sensory coding in free-energy-based reinforcement learning

Makoto Otsuka, Junichiro Yoshimoto, Kenji Doya

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

The free-energy-based reinforcement learning is a new approach to handling high-dimensional states and actions. We investigate its properties using a new experimental platform called the digit floor task. In this task, the highdimensional pixel data of hand-written digits were directly used as sensory inputs to the reinforcement learning agent. The simulation results showed the robustness of the free-energy-based reinforcement learning method against noise applied in both the training and testing phases. In addition, reward-dependent sensory representations were found in the distributed activation patterns of hidden units. The representations coded in a distributed fashion persisted even when the number of hidden nodes were varied.

Original languageEnglish
Pages (from-to)597-610
Number of pages14
JournalNeural Network World
Volume19
Issue number5
Publication statusPublished - 2009
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Software
  • Neuroscience(all)
  • Hardware and Architecture
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Reward-dependent sensory coding in free-energy-based reinforcement learning'. Together they form a unique fingerprint.

Cite this