Learning to Perceive and Act by Trial and Error |
| |
Authors: | Steven D Whitehead Dana H Ballard |
| |
Affiliation: | (1) Department of Computer Science, University of Rochester, Rochester, New York, 14627;(2) Department of Computer Science, University of Rochester, Rochester, New York, 14627 |
| |
Abstract: | This article considers adaptive control architectures that integrate active sensory-motor systems with decision systems based on reinforcement learning. One unavoidable consequence of active perception is that the agent's internal representation often confounds external world states. We call this phoenomenon perceptual aliasingand show that it destabilizes existing reinforcement learning algorithms with respect to the optimal decision policy. We then describe a new decision system that overcomes these difficulties for a restricted class of decision problems. The system incorporates a perceptual subcycle within the overall decision cycle and uses a modified learning algorithm to suppress the effects of perceptual aliasing. The result is a control architecture that learns not only how to solve a task but also where to focus its visual attention in order to collect necessary sensory information. |
| |
Keywords: | Reinforcement learning deictic representations sensory-motor integration hidden state non-Markov decision problems |
本文献已被 SpringerLink 等数据库收录! |