Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
Reinforcement learning with replacing eligibility traces
Machine Learning - Special issue on reinforcement learning
Machine Learning
Comparison of Several Machine Learning Techniques in Pursuit-Evasion Games
RoboCup 2001: Robot Soccer World Cup V
VQQL. Applying Vector Quantization to Reinforcement Learning
RoboCup-99: Robot Soccer World Cup III
HORUS: Object Orientation and Id without Additional Markers
RobVis '01 Proceedings of the International Workshop on Robot Vision
An agent-based approach to introductory robotics using robotic soccer
International Journal of Robotics and Automation
Hi-index | 0.00 |
This paper investigates the use of reinforcement learning in solving the path-tracking problem for car-like robots. The reinforcement learner uses a case-based function approximator, to extend the standard reinforcement learning paradigm to handle continuous states. The learned controller performs comparable to the best traditional control functions in both simulation and also in practical driving.