[Next] [Previous] [Top]

Contents

Contents

Abstract

1 - Motivation

2 - Criteria for a Good Model of Agent Learning

2.1 - Rigour

2.2 - Incrementality of the Learning Process

2.3 - Examinability of models learnt by the agents

2.4 - The existence of different trade-offs in model search

2.5 - The importance of the form of the agent's models

2.6 - Expressiveness of the Internal Language of Representation

2.7 - Practical to simulate

3 - Alternative learning paradigms

4 - Agent Models with defaults

5 - Criteria an agent might use in the search for a good internal model.

5.1 - Accuracy

5.2 - Measures of Model Specificity

5.2.1 - Generality

5.2.2 - Scope

5.2.3 - Precision

5.2.4 - Volume

5.3 - Cost

5.4 - Complexity

6 - Some Possible Agent Strategies

6.1 - Example strategies for agent model development

6.1.1 - Crossover

6.1.2 - Specializing the agent's model.

6.1.3 - Generalizing models of the agent.

7 - Towards a Specification of a Framework for Modelling Economic Learning by Modelling

7.1 - The General Framework

7.1.1 - The Space of Possibilities

7.1.2 - The Internal Language of Representation.

7.1.3 - The semantics of L

7.2 - A specification of the agent

7.3 - Assessing an internal model

7.3.1 - Error

7.3.2 - Complexity

7.3.3 - Volume

7.4 - Model search

7.5 - Action selection

8 - Some simple consequences of the framework

8.1 - The logic induced on L by m and PS.

8.2 - Response to Noise

9 - An Example Model - Utility Learning Agents

9.1 - General Description

9.2 - Formal Structure

9.3 - Implementation

9.4 - Results

10 - Conclusion

References

[Next] [Previous] [Top]

Generated with CERN WebMaker