2 papers
cs.LG2025
Rethinking the Foundations for Continual Reinforcement Learning
Esraa Elelimy, David Szepesvari, Martha White +1
In the traditional view of reinforcement learning, the agent's goal is to find an optimal policy that maximizes its expected sum of rewards. Once the agent finds this policy, the l…
cs.LG2025
A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning
Jacob Adkins, Michael Bowling, Adam White
The performance of modern reinforcement learning algorithms critically relies on tuning ever-increasing numbers of hyperparameters. Often, small changes in a hyperparameter can lea…