Národní úložiště šedé literatury Nalezeno 2 záznamů.  Hledání trvalo 0.01 vteřin. 
Q-learning used for control of AMB: reduced state definition
Březina, Tomáš ; Krejsa, Jiří
Previous work showed that stochastic strategy improved model free RL method known as Q-learning used on active magnetic bearing (AMB) model. So far the position, velocity and acceleration were used to describe the state of the system. This paper shows simplified version of controller which uses reduced state definition - position and velocity only. Furthermore the controlled initial conditions domain and its development during learning are shown.
Laplace's Demon vs Maxwell's Demon: From historical myths to topological evolution
Gottvald, Aleš
In sharp contrast with a common myth, Laplace appears as a pioneer of probabilistic determinism in science, with probabilities representing our incomplete knowledge. Thus, we warm that a completely false image of Laplace have developed in history of physics and philosophy. We introduce "Laplace's Demon" and "Maxwell's Demon" from an information-theoretic perspective,and indicate their omnipotent roles in physical theories, e.g., evolutionary laws with topological changes.

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.