Exploiting Causal Domain Knowledge for Learning to Control Dynamic Systems

This paper introduces a simple yete ective method for using causal domain knowledge for learning to control dynamic systems. Elementary qualitative causal dependencies of the domain are exploited in order to dramatically speed up the learning of reliable control strategies from a simulation model of the system. The reliability of the obtained control strategies is strengthened as well. The e ectiveness of the method has experimentally been studied at the problem of learning to balance a pole.

• Type: Conference
• Year: 1994
• Where: ECAI
• Authors: Achim G. Hoffmann
• Keywords: Artificial Intelligence, Causal Domain Knowledge, Control Strategies, ECAI 1994, Qualitative Causal Dependencies