Corpus ID: 1963904

Reinforcement Learning with Perceptual Aliasing: The Perceptual Distinctions Approach

@inproceedings{Chrisman1992ReinforcementLW,
  title={Reinforcement Learning with Perceptual Aliasing: The Perceptual Distinctions Approach},
  author={L. Chrisman},
  booktitle={AAAI},
  year={1992}
}
  • L. Chrisman
  • Published in AAAI 1992
  • Computer Science
    • It is known that Perceptual Aliasing may significantly diminish the effectiveness of reinforcement learning algorithms [Whitehead and Ballard, 1991. [...] Key Method 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 must also be learned, and to allow for stochastic actions and noisy perception, a probabilistic model is learned from experience. In the process, the system must discover, on its…Expand Abstract
    View Paper
    380 Citations
    Highly Influential Citations
    31
    Background Citations
    128
    Methods Citations
    101
    Results Citations
    1
    380 Citations
    Citation Type

    Citation Type

    Reinforcement Learning of Active Recognition Behaviors
    • 26
    Reinforcement learning to compensate for perceptual aliasing using dynamic additional parameter: motivational value
    • 6
    Reinforcement Learning of Perceptual Classes using Q Learning Updates
    • 8
    • PDF
    Greedy Utile Suux Memory for Reinforcement Learning with Perceptually-aliased States Keywords: Reinforcement Learning, Perceptual Aliasing, Instance-based Learning
    • Leonard A. BreslowNavy
    • 1996
    Resolving Perceptual Aliasing In The Presence Of Noisy Sensors
    • 22
    • PDF
    Learning with Incomplete Selective Perception
    • 7
    Bayesian Nonparametric Methods for Partially-Observable Reinforcement Learning
    • 3
    Learning in a State of Confusion: Perceptual Aliasing in Grid World Navigation
    • 32
    • PDF
    A Tutorial on Reinforcement Learning Techniques
    • 23
    • PDF
    Bayesian Nonparametric Methods for Partially-Observable Reinforcement Learning
    • 46
    • PDF

    References

    SHOWING 1-10 OF 31 REFERENCES
    Input Generalization in Delayed Reinforcement Learning: An Algorithm and Performance Comparisons
    • 286
    • PDF
    Learning in embedded systems
    • 731
    Cost-Sensitive Reinforcement Learning for Adaptive Classification and Control
    • M. Tan
    • Computer Science
    • AAAI
    • 1991
    • 37
    Scaling Reinforcement Learning Techniques via Modularity
    • 28
    A Complexity Analysis of Cooperative Mechanisms in Reinforcement Learning
    • 189
    • Highly Influential
    Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic Programming
    • 1,439
    • Highly Influential
    • PDF
    Forward Models: Supervised Learning with a Distal Teacher
    • 1,537
    • PDF
    Eecient Exploration in Reinforcement Learning
    • 41
    • PDF
    Programming Robots Using Reinforcement Learning and Teaching
    • 190
    Efficient Exploration In Reinforcement Learning
    • 222