Abstract
The problem considered in this chapter is how to use the observed behavior of organisms as a basis for machine learning. The proposed approach for machine learning combines near sets and ethology. It leads to novel forms of Q-learning algorithm that have practical applications in the controlling the behavior of machines, which learn to adapt to changing environments. Both traditional and new forms of adaptive learning theory and applications are considered in this chapter. A complete framework for an ethology-based approximate adaptive learning is established by using near sets.
TopAbstract
The problem considered in this chapter is how to use the observed behavior of organisms as a basis for machine learning. The proposed approach for machine learning combines near sets and ethology. It leads to novel forms of Q-learning algorithm that have practical applications in the controlling the behavior of machines, which learn to adapt to changing environments. Both traditional and new forms of adaptive learning theory and applications are considered in this chapter. A complete framework for an ethology-based approximate adaptive learning is established by using near sets.
TopIntroduction
The problem considered in this paper is how learning by a machine can adapt its behaviour to changing environmental conditions to achieve a better result. The solution to this problem hearkens back to the work of ethologist Niko Tinbergen (1940, 1942, 1948, 1951, 1953, 1963), starting in the 1940s. Tinbergen (1953b) suggested that the behaviour of swarms of interacting organisms and their environment make swarms be seen as individual. Of course, the insight in Tinbergen’s work augurs later by those who were interested in adaptive learning by societies of interacting machines. The work by Tinbergen and Konrad Lorenz (1981) led to the introduction of ethology, a comparative science of behaviour. The basic idea in the proposed approach to adaptive learning is to look behaviour of an organism as episodic and to record observed behaviours ethograms. An ethogram is a tabular representation of observed behaviours. An ethogram is a tabular representation of observed behaviours during an episode. Let si, ai, ri denote the ith state, action, reward, respectively. Reward ri results from performing action ai, where 0 ≤ i ≤ n for some finite, positive integer n. Each episode consists of a finite state-action-reward sequence of the form
. In this chapter, adaptive learning itself is observed at the individual level as well as at the society level.
Key Terms in this Chapter
Social Learning: Acquiring a new behaviour by watching or interacting with other animals.
Organism Behaviour: Tuples of behavior function values.
Ethogram: A tabular representation of observed behaviours.
Return: Cumulative future discounted rewards.
Near Sets: At least one object in a set has a description matching that of an object in another set.
Episode: A finite state-action-reward sequence.
Object Description: Tuple of function values.
Adaptive Learning: Behaviour modification in response to changes in the environment.