A Generalized Kalman Filter for Fixed Point Approximation and Efficient Temporal Difference Learning.
David ChoiBenjamin Van RoyPublished in: ICML (2001)
Keyphrases
- fixed point
- temporal difference learning
- kalman filter
- approximate value iteration
- object tracking
- sufficient conditions
- particle filter
- policy iteration
- mean shift
- evaluation function
- dynamical systems
- belief propagation
- state space
- computer vision
- neural network
- least squares
- function approximation
- three dimensional
- loss bounds