Strategy Learning with Multilayer Connectionist Representations

Strategy Learning with Multilayer Connectionist Representations (1987)

Cached

Download Links

by Charles W. Anderson

Venue:	In Proceedings of the Fourth International Workshop on Machine Learning
Citations:	65 - 4 self

BibTeX

@INPROCEEDINGS{Anderson87strategylearning,
    author = {Charles W. Anderson},
    title = {Strategy Learning with Multilayer Connectionist Representations},
    booktitle = {In Proceedings of the Fourth International Workshop on Machine Learning},
    year = {1987},
    pages = {103--114},
    publisher = {Morgan Kaufmann}
}

Bookmark

OpenURL

Abstract

Results are presented that demonstrate the learning and fine-tuning of search strategies using connectionist mechanisms. Previous studies of strategy learning within the symbolic, production-rule formalism have not addressed fine-tuning behavior. Here a two-layer connectionist system is presented that develops its search from a weak to a task-specific strategy and fine-tunes its performance. The system is applied to a simulated, realtime, balance-control task. We compare the performance of one-layer and two-layer networks, showing that the ability of the two-layer network to discover new features and thus enhance the original representation is critical to solving the balancing task.

Citations

2304	Learning Internal Representations by Error Propagation - Rumelhart, Hinton, et al. - 1986
1060	Learning to predict by the methods of temporal differences - Sutton - 1988
545	Some Studies in Machine Learning using the Game of Checkers - Samuel - 2000
157	Neuronlike elements that can solve difficult learning control problems - Barto, Sutton, et al. - 1983
147	Learning to predict by the methods of temporal di erence - Sutton - 1988
73	Experiments on Learning by BackPropagation - Plaut, Nowlan, et al. - 1986
49	Learning and problem solving with multilayer connectionist systems - Anderson - 1986
47	Training and Tracking in Robotics - Sutton, Barto - 1985
46	Learning by statistical cooperation of self-interested neuronlike computing elements." Humn Neurobiology - Barto - 1985
41	Associative search network: A reinforcement learning associative memory - Barto, Sutton, et al. - 1981
37	Learning to search: From weak methods to domain-specific heuristics - Langley - 1985
31	Production System Models of Learning and Development - Klahr - 1989
29	Dynamics of physical systems - Cannon - 1967
27	Neuronlike elements that can solve di cult learning control problems - Barto, Sutton, et al. - 1983
24	Learning automata—a survey - Narendra, Thathachar - 1974
11	Reinforcement learning control and pattern recognition systems - Mendel, McLaren - 1970
7	Temporal aspects of credit assignment in reinforcement learning - Sutton - 1984
2	Feature generation and selection by a layered network of reinforcement learning elements: some initial experiments - Anderson - 1982
2	A ball-balancing demonstration of optimal and disturbanceaccommodating control - Cheok - 1987
1	Doing, understanding, and production systems - Anzai - 1987