Modern reinforcement learning has been conditioned by at least three dogmas. The first is
the environment spotlight, which refers to our tendency to focus on modeling environments …

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 …

This paper analyzes reinforcement learning (RL) algorithms for Markov decision processes
(MDPs) under the average-reward criterion. We focus on Q-learning algorithms based on …

We show two average-reward off-policy control algorithms, Differential Q-learning (Wan,
Naik, & Sutton 2021a) and RVI Q-learning (Abounadi Bertsekas & Borkar 2001), converge in …

This paper investigates a new approach to model-based reinforcement learning using
background planning: mixing (approximate) dynamic programming updates and model-free …

This paper investigates a new approach to model-based reinforcement learning using
background planning: mixing (approximate) dynamic programming updates and model-free …

This paper studies asynchronous stochastic approximation (SA) algorithms and their
application to reinforcement learning in semi-Markov decision processes (SMDPs) with an …

We introduce a novel approach to hierarchical reinforcement learning for Linearly-solvable
Markov Decision Processes (LMDPs) in the infinite-horizon average-reward setting. Unlike …

The average-reward formulation is a natural and important formulation of learning and
planning problems, yet has received much less attention than the episodic and discounted …

In this paper, we study asynchronous stochastic approximation algorithms without
communication delays. Our main contribution is a stability proof for these algorithms that …