| Landmark based reward shaping in reinforcement learning with hidden states A Demir, E Çilden, F Polat Proceedings of the 18th International Conference on Autonomous Agents and …, 2019 | 13 | 2019 |
| Local roots: A tree-based subgoal discovery method to accelerate reinforcement learning A Demir, E Çilden, F Polat Machine Learning and Knowledge Discovery in Databases: European Conference …, 2016 | 8 | 2016 |
| Automatic landmark discovery for learning agents under partial observability A Demіr, E Çіlden, F Polat The Knowledge Engineering Review 34, e11, 2019 | 4 | 2019 |
| A concept filtering approach for diverse density to discover subgoals in reinforcement learning A Demir, E Cilden, F Polat 2017 IEEE 29th International Conference on Tools with Artificial …, 2017 | 4 | 2017 |
| A history tree heuristic to generate better initiation sets for options in reinforcement learning A Demir, E Çilden, F Polat ECAI 2016, 1644-1645, 2016 | 4 | 2016 |
| Generating effective initiation sets for subgoal-driven options A Demir, E Cilden, F Polat Advances in Complex Systems 22 (02), 1950001, 2019 | 3 | 2019 |
| Learning what to memorize: Using intrinsic motivation to form useful memory in partially observable reinforcement learning A Demir Applied Intelligence, 1-19, 2023 | 1 | 2023 |
| Landmark based guidance for reinforcement learning agents under partial observability A Demir, E Çilden, F Polat International Journal of Machine Learning and Cybernetics 14 (4), 1543-1563, 2023 | | 2023 |
| Behaviour Analysis of Izmir Residents Using Public Wi-Fi Access Point Usage İ Dilek, K Oğuz, A Demir 2022 3rd International Informatics and Software Engineering Conference …, 2022 | | 2022 |
| Effective subgoal discovery and option generation in reinforcement learning A Demir Middle East Technical University, 2016 | | 2016 |
Erkin ÇildenSTMstm.com.tr üzerinde doğrulanmış e-posta adresine sahip
