Two-Sample Testing in Reinforcement Learning. (arXiv:2201.08078v1 [cs.LG])

Value-based reinforcement-learning algorithms have shown strong performances
in games, robotics, and other real-world applications. The most popular
sample-based method is $Q$-Learning. A $Q$-value is the expected return for a
state-action pair when following a particular policy, and the algorithm
subsequently performs updates by adjusting the current $Q$-value towards the
observed reward and the maximum of the $Q$-values of the next state. The
procedure introduces maximization bias, and solutions like Double $Q$-Learning
have been considered. We frame the bias problem statistically …

arxiv learning reinforcement learning testing