| Using chains of bottleneck transitions to decompose and solve reinforcement learning tasks with hidden states H Aydın, E Çilden, F Polat Future Generation Computer Systems 133, 153-168, 2022 | 5 | 2022 |
| Population-based exploration in reinforcement learning through repulsive reward shaping using eligibility traces MI Bal, C Iyigun, F Polat, H Aydin Annals of Operations Research, 1-33, 2024 | 1 | 2024 |
| Compact Frequency Memory for Reinforcement Learning with Hidden States H Aydın, E Çilden, F Polat PRIMA 2019: Principles and Practice of Multi-Agent Systems: 22nd …, 2019 | 1 | 2019 |
| Using Transitional Bottlenecks to Improve Learning in Nearest Sequence Memory Algorithm H Aydın, E Çilden, F Polat 2017 IEEE 29th International Conference on Tools with Artificial …, 2017 | 1 | 2017 |
| Potential-based reward shaping using state-space segmentation for efficiency in reinforcement learning Mİ Bal, H Aydın, C İyigün, F Polat Future Generation Computer Systems, 2024 | | 2024 |
| Assisting Users in Privacy Conflicts with Partially Observable Multi-Agent Reinforcement Learning H Aydın HHAI 2024: Hybrid Human AI Systems for the Social Good, 55-63, 2024 | | 2024 |
| Using Frequencies of Transitions to Improve Reinforcement Learning with Hidden States H Aydın Middle East Technical University, 2022 | | 2022 |
| Automatic identification of transitional bottlenecks in reinforcement learning under partial observability H Aydın MIDDLE EAST TECHNICAL UNIVERSITY, 2017 | | 2017 |
| Self-management of patients with severe arthritis through a Personal Health System: The Turkish case study in the PALANTE project H Aydın, M Gençtürk, E Alpay, GB L Ertürkmen, A Doğaç | | 2015 |
