Recently, the impressive empirical success of policy gradient (PG) methods has catalyzed
the development of their theoretical foundations. Despite the huge efforts directed at the …

We consider infinite-horizon discounted Markov decision processes and study the
convergence rates of the natural policy gradient (NPG) and the Q-NPG methods with the log …

We consider the problem of designing sample efficient learning algorithms for infinite
horizon discounted reward Markov Decision Process. Specifically, we propose the …

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration
algorithms. Recent interest in Reinforcement Learning has motivated the study of methods …

The softmax policy gradient (PG) method, which performs gradient ascent under softmax
policy parameterization, is arguably one of the de facto implementations of policy …

We introduce algorithms based on natural actor-critic and analyze their sample complexity
for solving two player zero-sum Markov games in the tabular case. Our results improve the …

In this work, we study two-player zero-sum stochastic games and develop a variant of the
smoothed best-response learning dynamics that combines independent learning dynamics …

In this paper, we provide finite-sample convergence guarantees for an off-policy variant of
the natural actor-critic (NAC) algorithm based on Importance Sampling. In particular, we …

In this work, we study policy-based methods for solving the reinforcement learning problem,
where off-policy sampling and linear function approximation are employed for policy …

In this letter, we develop a novel variant of natural actor-critic algorithm using off-policy
sampling and linear function approximation, and establish a sample complexity of …