Neural Information Processing Systems http://nips.cc/

Thus the optimal average reward of the original MDP and modified MDP differ by O ( ϵ). To ensure Assumption 3.1 (b) is satisfied, an aperiodicity transformation can be implemented. The proof of this theorem can be found in [Sch71]. From Lemma 2.2, we thus have, ( J In order to iterate Equation (8), need to ensure the terms are non-negative. Theorem 3.3 presents an upper bound on the error in terms of the average reward.

Many policy-based reinforcement learning (RL) algorithms can be viewed as instantiations of approximate policy iteration (PI), i.e., where policy improvement and policy evaluation are both performed approximately. In applications where the average reward objective is the meaningful performance metric, often discounted reward formulations are used with the discount factor being close to $1,$ which is equivalent to making the expected horizon very large.

Neural Information Processing Systems http://nips.cc/

Many policy-based reinforcement learning (RL) algorithms can be viewed as instantiations of approximate policy iteration (PI), i.e., where policy improvement and policy evaluation are both performed approximately. In applications where the average reward objective is the meaningful performance metric, often discounted reward formulations are used with the discount factor being close to 1, which is equivalent to making the expected horizon very large. Thus, even after dividing the total reward by the length of the horizon, the corresponding performance bounds for average reward problems go to infinity. Therefore, an open problem has been to obtain meaningful performance bounds for approximate PI and RL algorithms for the average-reward setting. In this paper, we solve this open problem by obtaining the first non-trivial finite time error bounds for average-reward MDPs which go to zero in the limit as policy evaluation and policy improvement errors go to zero.

We study two time-scale linear stochastic approximation algorithms, which can be used to model well-known reinforcement learning algorithms such as GTD, GTD2, and TDC. We present finite-time performance bounds for the case where the learning rate is fixed. The key idea in obtaining these bounds is to use a Lyapunov function motivated by singular perturbation theory for linear differential equations. We use the bound to design an adaptive learning rate scheme which significantly improves the convergence rate over the known optimal polynomial decay rule in our experiments, and can be used to potentially improve the performance of any other schedule where the learning rate is changed at pre-determined time instants.

Record linkage involves merging records in large, noisy databases to remove duplicate entities. It has become an important area because of its widespread occurrence in bibliometrics, public health, official statistics production, political science, and beyond. Traditional linkage methods directly linking records to one another are computationally infeasible as the number of records grows. As a result, it is increasingly common for researchers to treat record linkage as a clustering task, in which each latent entity is associated with one or more noisy database records. We critically assess performance bounds using the Kullback-Leibler (KL) divergence under a Bayesian record linkage framework, making connections to Kolchin partition models. We provide an upper bound using the KL divergence and a lower bound on the minimum probability of misclassifying a latent entity. We give insights for when our bounds hold using simulated data and provide practical user guidance.

We consider the discrete-time infinite-horizon optimal control problem formalized by Markov Decision Processes (Puterman, 1994; Bertsekas and Tsitsiklis, 1996). We revisit the work of Bertsekas and Ioffe (1996), that introduced λ Policy Iteration, a family of algorithms parameterized by λ that generalizes the standard algorithms Value Iteration and Policy Iteration, and has some deep connections with the Temporal Differences algorithm TD(λ) described by Sutton and Barto (1998). We deepen the original theory developped by the authors by providing convergence rate bounds which generalize standard bounds for Value Iteration described for instance by Puterman (1994). Then, the main contribution of this paper is to develop the theory of this algorithm when it is used in an approximate form and show that this is sound. Doing so, we extend and unify the separate analyses developped by Munos for Approximate Value Iteration (Munos, 2007) and Approximate Policy Iteration (Munos, 2003). Eventually, we revisit the use of this algorithm in the training of a Tetris playing controller as originally done by Bertsekas and Ioffe (1996). We provide an original performance bound that can be applied to such an undiscounted control problem. Our empirical results are different from those of Bertsekas and Ioffe (which were originally qualified as "paradoxical" and "intriguing"), and much more conform to what one would expect from a learning experiment. We discuss the possible reason for such a difference.