Authors:
Eduardo Alonso
1
;
Esther Mondragón
2
and
Niclas Kjäll-Ohlsson
1
Affiliations:
1
City University London, United Kingdom
;
2
University College London, United Kingdom
Keyword(s):
Q-learning, IDQ-learning, Internal Drives, Convergence, Generalization.
Related
Ontology
Subjects/Areas/Topics:
Agents
;
Artificial Intelligence
;
Autonomous Systems
;
Cognitive Systems
;
Computational Intelligence
;
Evolutionary Computing
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Machine Learning
;
Soft Computing
;
Symbolic Systems
Abstract:
We present an approach to solving the reinforcement learning problem in which agents are provided with internal drives against which they evaluate the value of the states according to a similarity function. We extend Q-learning by substituting internally driven values for ad hoc rewards. The resulting algorithm, Internally Driven Q-learning (IDQ-learning), is experimentally proved to convergence to optimality and to generalize well. These results are preliminary yet encouraging: IDQ-learning is more psychologically plausible than Q-learning, and it devolves control and thus autonomy to agents that are otherwise at the mercy of the environment (i.e., of the designer).