[Bristol CS
| ISL
| Tim Kovacs
| Text
]
Strength or Accuracy: Credit Assignment in Learning Classifier Systems
Tim Kovacs
Back Cover Text
Machine learning promises both to create machine intelligence and to
shed light on natural intelligence. A fundamental issue for either
endevour is that of credit assignment, which we can pose as follows:
how can we credit individual components of a complex adaptive system
for their often subtle effects on the world?
For example, in a game of chess, how did each move (and the reasoning
behind it) contribute to the outcome?
This text studies aspects of credit assignment in Learning Classifier
Systems, which combine Evolutionary Algorithms with Reinforcement
Learning methods to address a range of tasks from pattern
classification to stochastic control to simulation of learning in
animals.
Credit assignment in classifier systems is complicated by two
features: 1) their components are frequently modified by evolutionary
search, and 2) components tend to interact.
Classifier systems are re-examined from first principles and the
result is, primarily, a formalisation of learning in these systems,
and a body of theory relating types of classifier systems, learning
tasks, and credit assignment pathologies.
Most significantly, it is shown that both of the main approaches have
difficulties with certain tasks which the other type does not.