5 papers
Relational-Grid-World: A Novel Relational Reasoning Environment and An Agent Model for Relational Information Extraction
Faruk Kucuksubasi, Elif Surer
Reinforcement learning (RL) agents are often designed specifically for a particular problem and they generally have uninterpretable working processes. Statistical methods-based age…
Using Generative Adversarial Nets on Atari Games for Feature Extraction in Deep Reinforcement Learning
Ayberk Aydın, Elif Surer
Deep Reinforcement Learning (DRL) has been successfully applied in several research domains such as robot navigation and automated video game playing. However, these methods requir…
Enhancing the Monte Carlo Tree Search Algorithm for Video Game Testing
Sinan Ariyurek, Aysu Betin-Can, Elif Surer
In this paper, we study the effects of several Monte Carlo Tree Search (MCTS) modifications for video game testing. Although MCTS modifications are highly studied in game playing,…
Developing a Scenario-Based Video Game Generation Framework: Preliminary Results
Elif Surer, Mustafa Erkayaoğlu, Zeynep Nur Öztürk +7
Emergency training and planning provide structured curricula, rule-based action items, and interdisciplinary collaborative entities to imitate and teach real-life tasks. This rule-…
Multi-modal Egocentric Activity Recognition using Audio-Visual Features
Mehmet Ali Arabacı, Fatih Özkan, Elif Surer +2
Egocentric activity recognition in first-person videos has an increasing importance with a variety of applications such as lifelogging, summarization, assisted-living and activity…