Is learning rate a good performance criterion for learning?
Proceedings of the seventh international conference (1990) on Machine learning
Deterministic autonomous systems
AI Magazine
ML92 Proceedings of the ninth international workshop on Machine learning
Neural networks: applications in industry, business and science
Communications of the ACM
Building symbolic representations of intuitive real-time skills from performance data
Machine intelligence 13
Inducing Models of human Control Skills
ECML '98 Proceedings of the 10th European Conference on Machine Learning
Learning to Fly: An Application of Hierarchical Reinforcement Learning
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
A Framework for Behavioural Cloning
Machine Intelligence 15, Intelligent Agents [St. Catherine's College, Oxford, July 1995]
Learning to Drive a Bicycle Using Reinforcement Learning and Shaping
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Skill reconstruction as induction of LQ controllers with subgoals
IJCAI'97 Proceedings of the Fifteenth international joint conference on Artifical intelligence - Volume 2
Hi-index | 0.00 |
The aim of behavioural cloning is to synthesize artificial controllers that are robust and comprehensible to human understanding. To attain the two objectives we propose the use of the Incremental Correction model that is based on a closed-loop control strategy to model the reactive aspects of human control skills. We have investigated the use of three different representations to encode the artificial controllers: univariate decision trees as induced by C4.5; multivariate decision and regression trees as induced by cart and; clausal theories induced by an Inductive Logic Programming (ILP) system. We obtained an increase in robustness and a lower complexity of the controllers when compared with results using other models. The controllers synthesized by cart revealed to be the most robust. The ILP system produced the simpler encodings.