## Abstract A robot needs the abilities of recognizing motion in the world (βotherβmotionβ), and generating βselfβmotionβ to adaptively behave in a real environment. We have been currently developing a system composed of an βotherβmotionβ recognition module and a βselfβmotionβ generation module. Th
Combining Hebbian and reinforcement learning in a minibrain model
β Scribed by R.J.C. Bosman; W.A. van Leeuwen; B. Wemmenhove
- Book ID
- 103853641
- Publisher
- Elsevier Science
- Year
- 2004
- Tongue
- English
- Weight
- 195 KB
- Volume
- 17
- Category
- Article
- ISSN
- 0893-6080
No coin nor oath required. For personal study only.
β¦ Synopsis
A toy model of a neural network in which both Hebbian learning and reinforcement learning occur is studied. The problem of 'path interference', which makes that the neural net quickly forgets previously learned input -output relations is tackled by adding a Hebbian term (proportional to the learning rate n) to the reinforcement term (proportional to d) in the learning rule. It is shown that the number of learning steps is reduced considerably if 1=4 , n=d , 1=2; i.e. if the Hebbian term is neither too small nor too large compared to the reinforcement term.
π SIMILAR VOLUMES
Reinforcement learning encompasses both a science of adaptive behavior of rational beings in uncertain environments and a computational methodology for finding optimal behaviors for challenging problems in control, optimization and adaptive behavior of intelligent agents. As a field, reinforcement l