Imitation learning of car driving skills with decision trees and random forests

• Published in: International journal of applied mathematics and computer science 2014-09, Vol.24 (3), p.579-597
• Main Authors: Cichosz, Paweł, Pawełczak, Łukasz
• Format: Article
• Language: English
• Subjects: Algorithms; Automobiles; Automotive engineering; autonomous driving; behavioral cloning; car racing; Computer simulation; control; Decision trees; imitation learning; Learning; Mathematical models; model ensembles; random forest; Retraining
• ISSN: 2083-8492; 1641-876X; 2083-8492
• DOI: 10.2478/amcs-2014-0042

Machine learning is an appealing and useful approach to creating vehicle control algorithms, both for simulated and real vehicles. One common learning scenario that is often possible to apply is learning by imitation, in which the behavior of an exemplary driver provides training instances for a supervised learning algorithm. This article follows this approach in the domain of simulated car racing, using the TORCS simulator. In contrast to most prior work on imitation learning, a symbolic decision tree knowledge representation is adopted, which combines potentially high accuracy with human readability, an advantage that can be important in many applications. Decision trees are demonstrated to be capable of representing high quality control models, reaching the performance level of sophisticated pre-designed algorithms. This is achieved by enhancing the basic imitation learning scenario to include active retraining, automatically triggered on control failures. It is also demonstrated how better stability and generalization can be achieved by sacrificing human-readability and using decision tree model ensembles. The methodology for learning control models contributed by this article can be hopefully applied to solve real-world control tasks, as well as to develop video game bots