A computational theory of adaptive behavior based on an evolutionary reinforcement mechanism

被引:0
作者
McDowell, J. J. [1 ]
Soto, Paul L. [2 ]
Dallery, Jesse [2 ]
Kulubekova, Saule [1 ]
机构
[1] Emory Univ, Dept Psychol, Atlanta, GA 30322 USA
[2] Univ Florida, Dept Psychol, Gainesville, FL 32611 USA
来源
GECCO 2006: GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, VOL 1 AND 2 | 2006年
关键词
evolutionary algorithms; reinforcement learning; adaptive behavior; adaptive agents; conditioned reinforcement; credit assignment; stimulus control; matching theory; delay-reduction theory; Rescorla-Wagner rule;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Two mathematical and two computational theories from the field of human and animal learning are combined to produce a more general theory of adaptive behavior. The cornerstone of this theory is an evolutionary algorithm for reinforcement learning that instantiates the idea that behavior evolves in response to selection pressure from the environment in the form of reinforcement. The evolutionary reinforcement algorithm, along with its associated equilibrium theory, are combined with a mathematical theory of conditioned reinforcement and a computational theory of associative learning that together solve the problem of credit assignment in a biologically plausible way. The result is a biologically-inspired computational theory that enables an artificial organism to adapt continuously to changing environmental conditions and to generate adaptive state-action sequences.
引用
收藏
页码:175 / +
页数:2
相关论文
共 15 条
[1]  
[Anonymous], 2004, Behavior analysis and learning
[2]   Equilibria of the Rescorla-Wagner model [J].
Danks, D .
JOURNAL OF MATHEMATICAL PSYCHOLOGY, 2003, 47 (02) :109-121
[3]  
DAVIDSON M, 1988, MATCHING LAW
[4]   ON THE LAW OF EFFECT [J].
Herrnstein, RJ .
JOURNAL OF THE EXPERIMENTAL ANALYSIS OF BEHAVIOR, 1970, 13 (02) :243-266
[5]   Reinforcement learning: A survey [J].
Kaelbling, LP ;
Littman, ML ;
Moore, AW .
JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 1996, 4 :237-285
[6]   TESTS OF AN EQUIVALENCE RULE FOR FIXED AND VARIABLE REINFORCER DELAYS [J].
MAZUR, JE .
JOURNAL OF EXPERIMENTAL PSYCHOLOGY-ANIMAL BEHAVIOR PROCESSES, 1984, 10 (04) :426-436
[7]   Choice, delay, probability, and conditioned reinforcement [J].
Mazur, JE .
ANIMAL LEARNING & BEHAVIOR, 1997, 25 (02) :131-147
[8]   On the classic and modern theories of matching [J].
McDowell, JJ .
JOURNAL OF THE EXPERIMENTAL ANALYSIS OF BEHAVIOR, 2005, 84 (01) :111-127
[9]   Computational model of selection by consequences [J].
McDowell, JJ .
JOURNAL OF THE EXPERIMENTAL ANALYSIS OF BEHAVIOR, 2004, 81 (03) :297-317
[10]   MATCHING THEORY IN NATURAL HUMAN ENVIRONMENTS [J].
MCDOWELL, JJ .
BEHAVIOR ANALYST, 1988, 11 (02) :95-109