Faruk Polat

E-mail

polatf@metu.edu.tr

Department

Department of Computer Engineering

ORCID

0000-0003-0509-9153

Scopus Author ID

7003321824

Web of Science Researcher ID

ABA-3585-2020

Subgoal identification with multiple instance learning methods in landmark Partially Observable Markov Decision Process problems Sunel, Saim; Polat, Faruk (2026-05-01)
Evaluation of Task Assignment Strategies for Capacitated Multi-Agent Pickup and Delivery in Automated Sortation Systems Çilden, Evren; Polat, Faruk (2026-01-01) Automated sortation has emerged as a major trend in logistics, enabling scalable and time-efficient sorting of items through the deployment of robotic agents. This study examines the use of capacity-enhanced agents in auto...
Task assignment strategies for capacitated agents engaged in lifelong pickup and delivery tasks Çilden, Evren; Polat, Faruk (2025-11-01) In this study, we tackled the task assignment problem in the capacity-enhanced version of Multi-Agent Pickup and Delivery (MAPD), a lifelong variant of the classical Multi-Agent Path Finding (MAPF) problem. Capacity-enhanc...
Relative distances approach for multi-traveling salesmen problem Ergüven, Emre; Polat, Faruk (2024-09-01)
Potential-based reward shaping using state–space segmentation for efficiency in reinforcement learning Bal, Melis İlayda; Aydın, Hüseyin; İyigün, Cem; Polat, Faruk (2024-08-01) Reinforcement Learning (RL) algorithms encounter slow learning in environments with sparse explicit reward structures due to the limited feedback available on the agent's behavior. This problem is exacerbated particularly ...
Faster MIL-based Subgoal Identification for Reinforcement Learning by Tuning Fewer Hyperparameters Sunel, Saim; Çilden, Erkin; Polat, Faruk (2024-4-20) Various methods have been proposed in the literature for identifying subgoals in discrete reinforcement learning (RL) tasks. Once subgoals are discovered, task decomposition methods can be employed to improve the learning ...
Population-based exploration in reinforcement learning through repulsive reward shaping using eligibility traces Bal, Melis Ilayda; İyigün, Cem; Polat, Faruk; Aydın, Hüseyin (2024-01-01) Efficient exploration plays a key role in accelerating the learning performance and sample efficiency of reinforcement learning tasks. In this paper we propose a framework that serves as a population-based repulsive reward...
Solving an industry-inspired generalization of lifelong MAPF problem including multiple delivery locations Polat, Faruk (2023-08-01)
Multiagent Pickup and Delivery for Capacitated Agents Çilden, Evren; Polat, Faruk (2022-01-01) In Multi-Agent Pickup and Delivery (MAPD), multiple robots continuously receive tasks to pick up packages and deliver them to predefined destinations in an automated warehouse. If the capacity of agents is increased, agent...
Landmark based guidance for reinforcement learning agents under partial observability Demir, Alper; Çilden, Erkin; Polat, Faruk (2022-01-01) Under partial observability, a reinforcement learning agent needs to estimate its true state by solely using its observation semantics. However, this interpretation has a drawback, which is called perceptual aliasing, avoi...

Citation Formats