Abstract
Reinforcement learning is a form of artificial intelligence in which an agent acquires and improves skills based on receiving positive and negative rewards when it performs actions within an environment. This paper describes a system which uses an extended reinforcement learning algorithm to generate reactive control strategies. It is applied to the control of a vehicle in a simulated traffic environment.
Original language | English |
---|---|
Pages | 437-445 |
Number of pages | 9 |
Publication status | Published - 1995 |
Event | Proceedings of the 1995 10th International Conference on Applications of Artificial Intelligence in Engineering, AIENG'95 - Udine, Italy Duration: 1 Jul 1995 → 1 Jul 1995 |
Conference
Conference | Proceedings of the 1995 10th International Conference on Applications of Artificial Intelligence in Engineering, AIENG'95 |
---|---|
City | Udine, Italy |
Period | 1/07/95 → 1/07/95 |