Abstract

It is known that Perceptual Aliasing may significantly diminish the effectiveness of reinforcement learning algorithms [ Whitehead and Ballard, 1991 ] . Perceptual aliasing occurs when multiple situations that are indistinguishable from immediate perceptual input require different responses from the system. For example, if a robot can only see forward, yet the presence of a battery charger behind it determines whether or not it should backup, immediate perception alone is insufficient for determining the most appropriate action. It is problematic since reinforcement algorithms typically learn a control policy from immediate perceptual input to the optimal choice of action. This paper introduces the predictive distinctions approach to compensate for perceptual aliasing caused from incomplete perception of the world. An additional component, a predictive model, is utilized to track aspects of the world that may not be visible at all times. In addition to the control policy, the model mus...

Citations

3116	A tutorial on hidden Markov models and selected applications in speech recognition - Rabiner - 1989
1135	Learning from delayed rewards - Watkins - 1989
573	A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains - Baum, Petrie, et al. - 1970
427	Integrated architectures for learning, planning, and reacting based on approximating integrated architectures for learning, planning, and reacting based on approximating dynamic programming - Sutton - 1990
316	Automatic programming of behavior-based robots using reinforcement learning - Mahadevan, Connell - 1992
280	Learning in embedded systems - Kaelbling - 1993
247	Forward models: Supervised learning with a distal teacher - Jordan, Rumelhart - 1992
165	Survey of partially observable markov decision processes: Theory, models, and algorithms - Monahan - 1982
158	Made-Up Minds: A Constructivist Approach to Artificial Intelligence - Drescher - 1991
151	A survey of algorithmic methods for partially observed Markov decision processes - Lovejoy - 1991
117	input generalization in delayed reinforcement learning: an algorithm and performance comparisons - Chapman, Kaelbling
113	Efficient exploration in reinforcement learning - Thrun - 1992
105	Realtime learning and control using asynchronous dynamic programmming - Baro, Bradtke, et al. - 1991
61	Programming robots using reinforcement learning and teaching - Lin - 1991
49	A complexity analysis of cooperative mechanisms in reinforcement learning - Whitehead - 1991
12	Intelligent agent design issues: Internal agent state and incomplete perception - Chrisman, Caruana, et al. - 1991
12	Cost-sensitive reinforcement learning for adaptive classification and control - Tan - 1991
4	Learning to avoid obstacles through reinforcement - Millan, Torras - 1991
4	Learning to perceive and act by trial and error, Machine Learning 7 - Whitehead, Ballard - 1991