4 papers
Accelerating Q-learning through Efficient Value-Sharing across Actions
Prabhat Nagarajan, Brett Daley, Martha White +1
Action values are foundational to many control algorithms such as Q-learning. Therefore, efficient action-value learning is central to reinforcement learning (RL). However, learnin…
Deep Double Q-learning
Prabhat Nagarajan, Martha White, Marlos C. Machado
Double Q-learning is a classical control algorithm that mitigates the maximization bias of Q-learning. To do so, it explicitly trains two independent action-value functions and use…
When is Offline Policy Selection Sample Efficient for Reinforcement Learning?
Vincent Liu, Prabhat Nagarajan, Andrew Patterson +1
Offline reinforcement learning algorithms often require careful hyperparameter tuning. Before deployment, we need to select amongst a set of candidate policies. However, there is l…
An Analysis of Action-Value Temporal-Difference Methods That Learn State Values
Brett Daley, Prabhat Nagarajan, Martha White +1
The hallmark feature of temporal-difference (TD) learning is bootstrapping: using value predictions to generate new value predictions. The vast majority of TD methods for control l…