Inductive Learning of Reactive Action Models
作者： Scott Benson
DOI: 10.1016/B978-1-55860-377-6.50015-3
关键词: Reactive agent 、 Golem 、 Multi-task learning 、 Action learning 、 Autonomous agent 、 Computer science 、 Artificial intelligence 、 Machine learning
摘要: … slow convergence of unsupervised exploration. continuously … models, it relies on the teacher less often. Figure 3 displays … We are currently examining methods of dealing with noise to …
elsevier.com
sci-hub.st 参考文章(21)
Marcel Schoppers, Building Plans to Monitor and Exploit Open-Loop and Closed-Loop Dynamics Artificial Intelligence Planning Systems. pp. 204- 213 ,(1992) , 10.1016/B978-0-08-049944-4.50029-X
Nils J. Nilsson, Scott Benson, Reacting, planning, and learning in an autonomous agent Machine intelligence. pp. 29- 62 ,(1996)
Claude Sammut, Scott Hurst, Dana Kedzier, Donald Michie, Learning to fly international conference on machine learning. pp. 385- 393 ,(1992) , 10.1016/B978-1-55860-247-2.50055-3
Xuemei Wang, Learning Planning Operators by Observation and Practice. AIPS. pp. 335- 340 ,(1994)
Sridhar Mahadevan, Enhancing Transfer in Reinforcement Learning by Building Stochastic Models of Robot Actions international conference on machine learning. pp. 290- 299 ,(1992) , 10.1016/B978-1-55860-247-2.50042-5
Yolanda Gil, Acquiring domain knowledge for planning by experimentation Carnegie Mellon University. ,(1992)
S. Muggleton, C. Feng, Efficient Induction of Logic Programs algorithmic learning theory. pp. 368- 381 ,(1990)
Sašo Džeroski, Stephen Muggleton, Stuart Russell, Learnability of constrained logic programs european conference on machine learning. pp. 342- 347 ,(1993) , 10.1007/3-540-56602-3_148
N. Nilsson, Teleo-reactive programs for agent control Journal of Artificial Intelligence Research. ,vol. 1, pp. 139- 158 ,(1993) , 10.1613/JAIR.30
Allen Newell, H.A. Simon, GPS, a program that simulates human thought Computation & intelligence. pp. 279- 293 ,(1995) , 10.1016/B978-1-4832-1446-7.50040-6