nips nips2003 nips2003-68 nips2003-68-reference knowledge-graph by maker-knowledge-mining

68 nips-2003-Eye Movements for Reward Maximization


Source: pdf

Author: Nathan Sprague, Dana Ballard

Abstract: Recent eye tracking studies in natural tasks suggest that there is a tight link between eye movements and goal directed motor actions. However, most existing models of human eye movements provide a bottom up account that relates visual attention to attributes of the visual scene. The purpose of this paper is to introduce a new model of human eye movements that directly ties eye movements to the ongoing demands of behavior. The basic idea is that eye movements serve to reduce uncertainty about environmental variables that are task relevant. A value is assigned to an eye movement by estimating the expected cost of the uncertainty that will result if the movement is not made. If there are several candidate eye movements, the one with the highest expected value is chosen. The model is illustrated using a humanoid graphic figure that navigates on a sidewalk in a virtual urban environment. Simulations show our protocol is superior to a simple round robin scheduling mechanism. 1


reference text

[1] M. F. Land and D. Lee. Where we look when we steer. Nature, 377, 1994.

[2] H. Shinoda, M. Hayhoe, and A. S Shrivastava. The coordination of eye, head, and hand movements in a natural task. Vision Research, 41, 2001.

[3] D. Ballard and N. Sprague. Attentional resource allocation in extended natural tasks [abstract]. Journal of Vision, 2(7):568a, 2002.

[4] L. Itti and C. Koch. Computational modeling of visual attention. Nature Reviews Neuroscience, 2(3):194–203, Mar 2001.

[5] L. Maloney and M. Landy. When uncertainty matters: the selection of rapid goal-directed movements [abstract]. Journal of Vision, (to appear).

[6] P. Waelti, A. Dickinson, and W. Schultz. Dopamine responses comply with basic assumptions of formal learning theory. Nature, 412, July 2001.

[7] Rodney A. Brooks. A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation, RA-2(1):14–23, April 1986.

[8] Leslie P. Kaelbling, Michael L. Littman, and Andrew W. Moore. Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 4:237–285, 1996.

[9] R.S. Sutton and A.G. Barto. Reinforcement Learning: An Introduction. MIT Press, 1998.

[10] M. Humphrys. Action selection methods using reinforcement learning. In Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior, 1996.

[11] J. Karlsson. Learning to Solve Multiple Goals. PhD thesis, University of Rochester, 1997.

[12] R. Sutton. Generalization in reinforcement learning: Successful examples using sparse coarse coding. In Advances in Neural Information Processing Systems, volume 8, 1996.

[13] N. Sprague and D. Ballard. Multiple-goal reinforcement learning with modular sarsa(0). In International Joint Conference on Artificial Intelligence, August 2003.

[14] N. Sprague and D. Ballard. Multiple goal learning for a virtual human. Technical Report 829, University Of Rochester Computer Science Department, 2004.

[15] R. E. Kalman. A new approach to linear filtering and prediction problems. Transactions of the ASME–Journal of Basic Engineering, 82(Series D):35–45, 1960.

[16] A. Cassandra. Exact and approximate algorithms for partially observable Markov decision processes. PhD thesis, Brown University, 1998.

[17] J. F. Seara, K. H. Strobl, E. Martin, and G. Schmidt. Task-oriented and sitaution-dependent gaze control for vision guided autonomous walking. In Proceedings of the 3rd IEEE-RAS International Conference on Humanoid Robots, 2003.