Presentation | 2003/12/1 Simulation of Rat's behavior in conflict of approach and avoidance by reinforcement learning in cosideration of appearance probabilities of reinforcement signals Takuya NOGUCHI, Kazushi MURAKOSHI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Brown et al. (1964) investigated rat's behavior with the following features: (1) reward and punishment are provided at the same time, (2) rats relearn after environment changes, and (3) reward and punishment are provided with probabilities. The results are that exposure to nonreinforcement produces resistance to the decrernental effects of behavior after stochastic reward schedule and that exposure to both punishment and reinforcement produces resistance to the decremental effects of behavior after stochastic punishment schedule. This paper aims to simulate the rat's behabior in conflict of approach and avoidance by reinforcement learning in consideration of appearance probabilities of reinforcement signals. The former algorithms of reinforcement learning could not simulate the behavior of the feature (3). We improve the former reinforcement learning algorithms by controlling learning parameters in consideration of the acquisition probabilities of reinforcement signals. Our algorithm qualitatively simulates the result of the animal experiment of Brown et al. (1964). |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Reinforcement learning / Rat's behavior / Learning parameter control / Appearance probability of reinforcement signal |
Paper # | NC2003-98 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2003/12/1(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Neurocomputing (NC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Simulation of Rat's behavior in conflict of approach and avoidance by reinforcement learning in cosideration of appearance probabilities of reinforcement signals |
Sub Title (in English) | |
Keyword(1) | Reinforcement learning |
Keyword(2) | Rat's behavior |
Keyword(3) | Learning parameter control |
Keyword(4) | Appearance probability of reinforcement signal |
1st Author's Name | Takuya NOGUCHI |
1st Author's Affiliation | Department of Knowledge-based Information Engineering, Toyohashi University of Technology() |
2nd Author's Name | Kazushi MURAKOSHI |
2nd Author's Affiliation | Department of Knowledge-based Information Engineering, Toyohashi University of Technology |
Date | 2003/12/1 |
Paper # | NC2003-98 |
Volume (vol) | vol.103 |
Number (no) | 490 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |