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

Title:

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

Creator:

Otsuka, Makoto, Yoshimoto, Junichiro , and Doya, Kenji

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:9a7d0f68-3e69-43eb-b72d-a05d7d8cadb2
uuid:9a7d0f68-3e69-43eb-b72d-a05d7d8cadb2

Subject:

Reinforcement learning, noise tolerance, population coding, reward-dependent and -invariant representations, restricted, and Boltzmann machines

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

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 high-dimensional 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.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Neural network world: international journal on neural and mass-parallel computing and information systems | 2009 Volume:19 | Number:5

Harvested from:

CDK

Metadata only:

false