Czech
EnglishIn imitation learning (IL) an agent learns optimal policy from expert demonstrations. Among the classical approaches used for solving IL there are behavioral cloning that learns a policy via a...
Ústav teorie informace a automatizace
Jste zde
Seminars AS
10.10.2022 - 11:00
Přednášející: Ing. Kamil Dedecius, Ph.D.
Místnost: 474
The state-of-the-art algorithms for Kalman filtering in agent networks with information diffusion mostly assume that both the process and measurement noise covariance matrices are known. In the...