Naslov
Reinforcement learning in simulated systems

Autori
Livaja, Vladimir Dragutin

Vrsta, podvrsta i kategorija rada
Ocjenski radovi, diplomski rad, diplomski

Fakultet
Fakultet elektrotehnike i računarstva

Mjesto
Zagreb

Datum
09.07

Godina
2018

Stranica
50

Mentor
Pripužić, Krešimir

Ključne riječi
podržano učenje, neuronske mreže ; agent ; okruženje ; Q vrijednosti ; vrijednost stanja ; povratne mreže ; iskusno ponavljanje
(Reinforcement learning ; agent ; environment ; deep neural networks ; Q values ; state values ; experience replay ; recurrent networks.)

Sažetak
In this thesis we focused on implementing a reinforcement agent that was able to generalize to various simulated systems and in doing so ; showed the ability of the reinforcement learning algorithm to adapt. Fundamentals of deep learning were also described. Using Tensorflow, a reinforcement learning agent was implemented. The agent was evaluated on three different scenarios: Pacman from the Atari 2600 games and two different scenarios of the game Doom. The evaluation results were shown via graphs.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo

POVEZANOST RADA