Learn More
for helping to clarify the relationships between heuristic search and control. We thank Rich Sutton, Chris Watkins, Paul Werbos, and Ron Williams for sharing their fundamental insights into this subject through numerous discussions , and we further thank Rich Sutton for rst making us aware of Korf's research and for his very thoughtful comments on the(More)
We introduce two new temporal diffence (TD) algorithms based on the theory of linear least-squares function approximation. We define an algorithm we call Least-Squares TD (LS TD) for which we prove probability-one convergence when it is used with a function approximator linear in the adjustable parameters. We then define a recursive version of this(More)
Semi-Markov Decision Problems are continuous time generalizations of discrete time Markov Decision Problems. A number of reinforcement learning algorithms have been developed recently for the solution of Markov Decision Problems, based on the ideas of asynchronous dynamic programming and stochastic approximation. Among these are TD(), Q-learning, and(More)
In this paper we present stability and convergence results for Dynamic Programming-based reinforcement learning applied to Linear Quadratic Regulation (LQR). The spe-ciic algorithm we analyze is based on Q-learning and it is proven to converge to the optimal controller provided that the underlying system is controllable and a particular signal vector is(More)
for helping to clarify the relationships between heuristic search and control. We thank Rich Sutton, Chris Watkins, Paul Werbos, and Ron Williams for sharing their fundamental insights into this subject through numerous discussions , and we further thank Rich Sutton for rst making us aware of Korf's research and for his very thoughtful comments on the(More)
[3] R. Rimey and C. Brown. Control of selective perception using bayes nets and decision theory .ing to act using real-time dynamic programming. [9] Vadim Bulitko and Ilya Levner. Improving learn-ability of adaptive image interpretation systems. An optimal algorithm for approximate nearest neighbor searching fixed dimensions. [17] Dan Pelleg and Andrew(More)
  • 1