Task Decomposition Through Competition in a Modular Connectionist Architecture: The What and Where Vision Tasks
Robert A. Jacobs(Massachusetts Institute of Technology), Andrew G. Barto(University of Massachusetts Amherst), Michael I. Jordan(University of California, Berkeley)
Cited by 497
Related Papers
Introduction to Reinforcement Learning
|MIT Press eBooks|1998|6.9k
Reinforcement Learning
|IFAC Proceedings Volumes|1998|3k
Toward a modern theory of adaptive networks: Expectation and prediction.
|Psychological Review|1981|1.5k
Learning to act using real-time dynamic programming
|Artificial Intelligence|1995|1.1k
Recent Advances in Hierarchical Reinforcement Learning
|Discrete Event Dynamic Systems|2003|1k