| Autor: |
Yamaguchi, Yoshiya, Sakai, Yutaka |
| Zdroj: |
6th International Conference on Soft Computing & Intelligent Systems & The 13th International Symposium on Advanced Intelligence Systems; 2012, p1182-1185, 4p |
| Abstrakt: |
Humans and other animals often prefer small, short-delayed rewards to large, long-delayed rewards. A standard interpretation is that such impulsive preference might originate in the subjective reward value that is temporally discounted. Although this interpretation is consistent with animal's impulsive choice behavior observed in many studies, the biological significance remains unclear. Another interpretation is that impulsive preference might originate in reward-maximization failure while animals might attempt to maximize the physical amount of reward. We introduced a synaptic learning rule for reward-maximization to simulate in a standard inter-temporal choice task for non-human animals. As a result, on the assumption that animals do not discriminate the states after one choice from that after another, a synaptic learning rule with long-tailed eligibility traces reproduced animals' impulsive preference. [ABSTRACT FROM PUBLISHER] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
