Using Generative Adversarial Nets on Atari Games for Feature Extraction in Deep Reinforcement Learning

Date

2020-10-07

Author

Aydin, Ayberk
Sürer, Elif

Metadata

Show full item record

Item Usage Stats

48
views

0
downloads

URI

https://hdl.handle.net/11511/82844

Collections

Unverified, Conference / Seminar

Suggestions

OpenMETU
Core

Using Generative Adversarial Nets on Atari Games for Feature Extraction in Deep Reinforcement Learning Aydın, Ayberk; Sürer, Elif (2020-04-01) Deep Reinforcement Learning (DRL) has been suc-cessfully applied in several research domains such as robotnavigation and automated video game playing. However, thesemethods require excessive computation and interaction with theenvironment, so enhancements on sample efficiency are required.The main reason for this requirement is that sparse and delayedrewards do not provide an effective supervision for representationlearning of deep neural networks. In this study, Proximal Policy...
Using Generative Adversarial Nets on Atari Games for Feature Extraction in Deep Reinforcement Learning Aydın, Ayberk; Sürer, Elif (2020-10-05) Deep Reinforcement Learning (DRL) has been successfully applied in several research domains such as robot navigation and automated video game playing. However, these methods require excessive computation and interaction with the environment, so enhancements on sample efficiency are required. The main reason for this requirement is that sparse and delayed rewards do not provide an effective supervision for representation learning of deep neural networks. In this study, Proximal Policy Optimization (PPO) algo...
Using Multi-Agent Reinforcement Learning in Auction Simulations Kanmaz, Medet; Sürer, Elif (2020-04-01) Game theory has been developed by scientists as a theory of strategic interaction among players who are supposed to be perfectly rational. These strategic interactions might have been presented in an auction, a business negotiation, a chess game, or even in a political conflict aroused between different agents. In this study, the strategic (rational) agents created by reinforcement learning algorithms are supposed to be bidder agents in various types of auction mechanisms such as British Auction, Sealed Bid...
Using collaboration diagrams in component oriented modelin Tuncel, Mehmet Burhan; Doğru, Ali Hikmet; Department of Computer Engineering (2006) Component Oriented Software Engineering (COSE) seems to be the future of software engineering. Currently, COSEML is the only modeling language that completely supports the COSE approach. Abstract decomposition of the system and their representing components are shown in a hierarchy diagram to support the COSE process model. In COSEML, only static modeling is supported through this single diagram. However, software is about behavior and static modeling is not sufficient to describe the system. The aim of thi...
Using fuzzy Petri nets for static analysis of rule-bases Bostan-Korpeoglu, B; Yazıcı, Adnan (2004-01-01) We use a Fuzzy Petri Net (FPN) structure to represent knowledge and model the behavior in our intelligent object-oriented database environment, which integrates fuzzy, active and deductive rules with database objects. However, the behavior of a system can be unpredictable due to the rules triggering or untriggering each other (non-termination). Intermediate and final database states may also differ according to the order of rule executions (non-confluence). In order to foresee and solve problematic behavior...

Citation Formats

A. Aydin and E. Sürer, “Using Generative Adversarial Nets on Atari Games for Feature Extraction in Deep Reinforcement Learning,” 2020, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/82844.