Convergence Results for Some Temporal Difference Methods Based on Least Squares

We consider finite-state Markov decision processes, and prove convergence and rate of convergence results for certain least squares policy evaluation algorithms of the type known as LSPE(lambda ). These are temporal difference methods for constructing a linear function approximation of the cost function of a stationary policy, within the context of infinite-horizon discounted and average cost dynamic programming. We introduce an average cost method, patterned after the known discounted cost method, and we prove its convergence for a range of constant stepsize choices. We also show that the convergence rate of both the discounted and the average cost methods is optimal within the class of temporal difference methods. Analysis and experiment indicate that our methods are substantially and often dramatically faster than TD(lambda), as well as more reliable.