Shaping: A multiple contingencies analysis and its relevance to behaviour-based robotics

Savage, Tony

doi:10.1080/09540090110096196

Cited by 7 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Behavioral variability sometimes results when reinforcement is withheld, as indicated above (Savage, 2001), as well as from physiological injury and drugs (Brugger, 1997), but such variability appears to be of a different type than that under discussion; it is elicited or reflexive in nature, and, although it might contribute, elicited variation will not account for the reinforcement effects described above-the yoke control procedures show that. Three additional explanations of operant variability will be discussed in this section.…”

Section: Sources Of Operant Variabilitymentioning

confidence: 99%

Reinforced Variability in Animals and People: Implications for Adaptive Action.

Neuringer¹

2004

American Psychologist

109

View full text Add to dashboard Cite

Section: Sources Of Operant Variabilitymentioning

confidence: 99%

Reinforced Variability in Animals and People: Implications for Adaptive Action.

Neuringer¹

2004

American Psychologist

109

View full text Add to dashboard Cite

“…However, simplified models can serve as a baseline for creating a series of more complex models needed to represent classes of observed behavior (Wimsatt, 1987). Savage (1998) and Savage (2001) discuss the complexities and potential of creating robot (physical agent) algorithms that are rooted in animal learning. They emphasize the need for variability and the role of extinction in producing variability of actions that lead to better animal learning approximations.…”

Section: Discussionmentioning

confidence: 99%

Sequence-Learning Algorithm Based on Backward Chaining

Joshi

Guilhabert

2006

Adaptive Behavior

View full text Add to dashboard Cite

This article considers the problem of learning the correct temporal sequence of discrete behaviors from a finite behavior set that will lead to completion of a complex task, using only stochastic reinforcement from the environment. A trial-and-error learning algorithm is proposed that is inspired by backward chaining from the animal training discipline. The procedure is analytically formulated using a serial composition of finite action-set learning automata with delay. Simulation of the proposed algorithm shows that the algorithm does indeed lead to sequence learning. The effect of parametric variation in the magnitude and quality of reinforcement is investigated in both theory and simulation. It is shown that a fundamental tradeoff exists between quality and speed of learning. It is also shown that the algorithm has the ability to learn desirable action sequences among several feasible action sequences through the use of relative rewards, which may be interpreted using the Bellman principle of optimality.

show abstract

“…At the same time, we continue to be rightly impressed by demonstrations of its effectiveness, for example, in teaching speech to individuals who lack it (e.g., Isaacs, Thomas, & Goldiamond, 1960;Lovaas, Berberich, Perdoff, & Schaeffer, 1960), or, more recently, in helping individuals with brain damage recover lost limb function even after many years of nonuse (e.g., Taub et al, 1994). And in the futuristic field of artificial intelligence, a generic capacity for behavior to be shaped by its consequences is recognized as key to eventual success in the design of versatile robots (e.g., Saksida, Raymond, & Toutetzky, 1997;Savage, 1998Savage, , 2001. Thus B. F. Skinner's studies of response differentiation and his subsequent insight about shaping, each a genuinely original set of observations, deserve to be delineated among the most important findings, in terms of both theoretical and practical significance, in the history of behavioral science.…”

Section: Dear Miss Schradermentioning

confidence: 99%

A Day of Great Illumination: B. F. Skinner's Discovery of Shaping

Peterson

2004

J Exper Analysis Behavior

122

View full text Add to dashboard Cite

Despite the seminal studies of response differentiation by the method of successive approximation detailed in chapter 8 of The Behavior of Organisms (1938), B. F. Skinner never actually shaped an operant response by hand until a memorable incident of startling serendipity on the top floor of a flour mill in Minneapolis in 1943. That occasion appears to have been a genuine eureka experience for Skinner, causing him to appreciate as never before the significance of reinforcement mediated by biological connections with the animate social environment, as opposed to purely mechanical connections with the inanimate physical environment. This insight stimulated him to coin a new term (shaping), and also led directly to a shift in his perspective on verbal behavior from an emphasis on antecedents and molecular topographical details to an emphasis on consequences and more molar, functional properties in which the social dyad inherent to the shaping process became the definitive property of verbal behavior. Moreover, the insight seems to have emboldened Skinner to explore the greater implications of his behaviorism for human behavior writ large, an enterprise that characterized the bulk of his post-World War II scholarship.

show abstract

Shaping: A multiple contingencies analysis and its relevance to behaviour-based robotics

Cited by 7 publications

References 28 publications

Reinforced Variability in Animals and People: Implications for Adaptive Action.

Reinforced Variability in Animals and People: Implications for Adaptive Action.

Sequence-Learning Algorithm Based on Backward Chaining

A Day of Great Illumination: B. F. Skinner's Discovery of Shaping

Contact Info

Product

Resources

About