2 papers
cs.LG2019
Robust Visual Domain Randomization for Reinforcement Learning
Reda Bahi Slaoui, William R. Clements, Jakob N. Foerster +1
Producing agents that can generalize to a wide range of visually different environments is a significant challenge in reinforcement learning. One method for overcoming this issue i…
cs.LG2019
Estimating Risk and Uncertainty in Deep Reinforcement Learning
William R. Clements, Bastien Van Delft, Benoît-Marie Robaglia +2
Reinforcement learning agents are faced with two types of uncertainty. Epistemic uncertainty stems from limited data and is useful for exploration, whereas aleatoric uncertainty ar…