Arşiv ve Dokümantasyon Merkezi
Dijital Arşivi

The effect of game complexity on deep reinforcement learning

Basit öğe kaydını göster

dc.contributor Graduate Program in Computer Engineering.
dc.contributor.advisor Alpaydın, ethem.
dc.contributor.author Emekligil, Erdem.
dc.date.accessioned 2023-03-16T10:03:02Z
dc.date.available 2023-03-16T10:03:02Z
dc.date.issued 2018.
dc.identifier.other CMPE 2018 E53
dc.identifier.uri http://digitalarchive.boun.edu.tr/handle/123456789/12353
dc.description.abstract Deep Reinforcement Learning (DRL) combines deep neural networks with re inforcement learning. These methods, unlike their predecessors, learn end-to-end by extracting high-dimensional representations from raw sensory data to directly predict the actions. DRL methods were shown to master most of the ATARI games, beating humans in a good number of them, using the same algorithm, network architecture and hyper-parameters. However, why DRL works on some games better than others has not been fully investigated. In this thesis, we propose that the complexity of each game is defined by a number of factors (the size of the search space, existence/absence of enemies, existence/absence of intermediate reward, and so on) and we posit that how fast and well a game is learned by DRL depends on these factors. Towards this aim, we use simplified Maze and Pacman environments and we conduct experiments to see the effect of such factors on the convergence of DRL. Our results provide a first step in a better understanding of how DRL works and as such will be informative in the future in determining scenarios where DRL can be applied effectively e.g., outside of games.
dc.format.extent 30 cm.
dc.publisher Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018.
dc.subject.lcsh Reinforcement learning (Machine learning)
dc.subject.lcsh Game theory.
dc.title The effect of game complexity on deep reinforcement learning
dc.format.pages xv, 78 leaves ;


Bu öğenin dosyaları

Bu öğe aşağıdaki koleksiyon(lar)da görünmektedir.

Basit öğe kaydını göster

Dijital Arşivde Ara


Göz at

Hesabım