In this paper, we address two issues of long-standing interest in the re(cid:173) inforcement learning literature. First, what kinds of performance guar(cid:173) antees can be made for Q-learning after only a finite number of actions? Second, what quantitative comparisons can be made between Q-learning and model-based (indirect) approaches, which use experience to estimate next-state distributions for off-line value iteration? We first show that both Q-learning and the indirect approach enjoy rather rapid convergence to the optimal policy as a function of the num(cid:173) ber of state transitions observed. In particular, on the order of only (Nlog(1/c)/c2)(log(N) loglog(l/c)) transitions are sufficient for both algorithms to come within c of the optimal policy, in an idealized model that assumes the observed transitions are "well-mixed" throughout an N-state MDP.

In this paper, we address two issues of longstanding interest in the reinforcement learning literature. First, what kinds of performance guarantees can be made for Q-learning after only a finite number of actions? Second, what quantitative comparisons can be made between Q-learning and model-based (indirect) approaches, which use experience to estimate next-state distributions for off-line value iteration? We first show that both Q-learning and the indirect approach enjoy rather rapid convergence to the optimal policy as a function of the number of state transitions observed.

In this paper, we address two issues of longstanding interest in the reinforcement learning literature. First, what kinds of performance guarantees can be made for Q-learning after only a finite number of actions? Second, what quantitative comparisons can be made between Q-learning and model-based (indirect) approaches, which use experience to estimate next-state distributions for off-line value iteration? We first show that both Q-learning and the indirect approach enjoy rather rapid convergence to the optimal policy as a function of the number of state transitions observed.

In this paper, we address two issues of longstanding interest in the reinforcement learningliterature. First, what kinds of performance guarantees can be made for Q-learning after only a finite number of actions? Second, what quantitative comparisons can be made between Q-learning and model-based (indirect) approaches, which use experience to estimate next-state distributions for off-line value iteration? We first show that both Q-learning and the indirect approach enjoy rather rapid convergence to the optimal policy as a function of the number ofstate transitions observed.