Optimization algorithms are used to improve model accuracy. The optimization process
undergoes multiple cycles until convergence. A variety of optimization strategies have been …

Whittle index policy is a heuristic to the intractable restless multi-armed bandits (RMAB)
problem. Although it is provably asymptotically optimal, finding Whittle indices remains …

We consider experiments in dynamical systems where interventions on some experimental
units impact other units through a limiting constraint (such as a limited supply of products) …

The deadly triad refers to the instability of a reinforcement learning algorithm when it
employs off-policy learning, function approximation, and bootstrapping simultaneously. In …

The focus of this paper is on sample complexity guarantees of average-reward
reinforcement learning algorithms, which are known to be more challenging to study than …

Abstract Robust Markov decision processes (MDPs) address the challenge of model
uncertainty by optimizing the worst-case performance over an uncertainty set of MDPs. In …

This work studies the statistical limits of uniform convergence for offline policy evaluation
(OPE) problems with model-based methods (for episodic MDP) and provides a unified …

We study average-reward Markov decision processes (AMDPs) and develop novel first-
order methods with strong theoretical guarantees for both policy optimization and policy …

The average reward criterion is relatively less studied as most existing works in the
Reinforcement Learning literature consider the discounted reward criterion. There are few …

Off-policy learning is a key to extend reinforcement learning as it allows to learn a target
policy from a different behavior policy that generates the data. However, it is well known as …