Dyna, an integrated architecture for learning, planning, and reacting
关键词: Robot learning 、 Action (philosophy) 、 Active learning (machine learning) 、 Algorithmic learning theory 、 Architecture 、 Computer science 、 Artificial intelligence 、 Probabilistic logic 、 Computational learning theory 、 Strengths and weaknesses
摘要: … The structure and learning of the action model lie mostly outside the the scope of the Dyna … the scope of the Dyna architecture per se. Because Dyna makes no strong assumptions …
acm.org
core.ac.uk
sci-hub.se 参考文章(18)
Rick L. Riolo, Lookahead planning and latent learning in a classifier system simulation of adaptive behavior. pp. 316- 326 ,(1991)
Richard S. Sutton, Integrated architecture for learning, planning, and reacting based on approximating dynamic programming international conference on machine learning. pp. 216- 224 ,(1990) , 10.1016/B978-1-55860-141-3.50030-4
Long-Ji Lin, Self-improving reactive agents: case studies of reinforcement learning frameworks simulation of adaptive behavior. pp. 297- 305 ,(1991)
Dimitri P. Bertsekas, Dynamic Programming: Deterministic and Stochastic Models ,(1987)
Richard Stuart Sutton, Temporal credit assignment in reinforcement learning University of Massachusetts Amherst. ,(1984)
A. G. Barto, R. S. Sutton, C. J.C.H. Watkins, Learning and Sequential Decision Making University of Massachusetts. ,(1989)
Stuart J. Russell, Execution architectures and compilation international joint conference on artificial intelligence. pp. 15- 20 ,(1989)
Leslie Pack Kaelbling, Nils J. Nilsson, Learning in Embedded Systems ,(1993)
Paul Werbos, Building and Understanding Adaptive Systems: A Statistical/Numerical Approach to Factory Automation and Brain Research systems man and cybernetics. ,vol. 17, pp. 7- 20 ,(1987) , 10.1109/TSMC.1987.289329
Kenneth James Williams Craik, The nature of explanation ,(1943)