17 citations · 17 across the 4 of their papers we have counts for
4 papers
Approximate discounting-free policy evaluation from transient and recurrent states
Vektor Dewanto, Marcus Gallagher
In order to distinguish policies that prescribe good from bad actions in transient states, we need to evaluate the so-called bias of a policy from transient states. However, we obs…
Examining average and discounted reward optimality criteria in reinforcement learning
Vektor Dewanto, Marcus Gallagher
In reinforcement learning (RL), the goal is to obtain an optimal policy, for which the optimality criterion is fundamentally important. Two major optimality criteria are average an…
A nearly Blackwell-optimal policy gradient method
Vektor Dewanto, Marcus Gallagher
For continuing environments, reinforcement learning (RL) methods commonly maximize the discounted reward criterion with discount factor close to 1 in order to approximate the avera…
Average-reward model-free reinforcement learning: a systematic review and literature mapping
Vektor Dewanto, George Dunn, Ali Eshragh +2
Reinforcement learning is important part of artificial intelligence. In this paper, we review model-free reinforcement learning that utilizes the average reward optimality criterio…