December
1999
Q-Learning in Continuous State and Action Spaces
Authors:
Abstract:
Q-learning can be used to learn a control policy that maximises a scalar reward through interaction with the environment. Q-learning is commonly applied to problems with discrete states and actions. We describe a method suitable for control tasks which require continuous actions, in response to continuous states. The system consists of a neural network coupled with a novel interpolator. Simulation results are presented for a non-holonomic control task. Advantage Learning, a variation of Q-learning, is shown enhance learning speed and reliability for this task.
copied = false, 2000);
">
@conference{Gaskett-1999-120376,
author = {C. Gaskett And D. Wettergreen And A. Zelinsky},
title = {Q-Learning in Continuous State and Action Spaces},
booktitle = {Proceedings of 12th Australasian Joint Conference on Artificial Intelligence (AI '99)},
year = {1999},
month = {December},
pages = {417 - 428},
}
author = {C. Gaskett And D. Wettergreen And A. Zelinsky},
title = {Q-Learning in Continuous State and Action Spaces},
booktitle = {Proceedings of 12th Australasian Joint Conference on Artificial Intelligence (AI '99)},
year = {1999},
month = {December},
pages = {417 - 428},
}