Active Learning by Query by Committee with Robust Divergences

no code implementations • 18 Nov 2022 • Hideitsu Hino, Shinto Eguchi

In this paper, the measure of disagreement is defined by the Bregman divergence, which includes the Kullback--Leibler divergence as an instance, and the dual $\gamma$-power divergence.

Active Learning

Minimum information divergence of Q-functions for dynamic treatment resumes

no code implementations • 16 Nov 2022 • Shinto Eguchi

In a standard framework of reinforcement learning, a Q-function is defined as the conditional expectation of a reward given a state and an action for a single-stage situation.

reinforcement-learning Reinforcement Learning (RL)