| 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 | 20 | 2019 |
| Toward generalization of automated temporal abstraction to partially observable reinforcement learning E Cilden, F Polat IEEE Transactions on Cybernetics 45 (8), 1414-1425, 2014 | 15 | 2014 |
| 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 |
| Generating memoryless policies faster using automatic temporal abstractions for reinforcement learning with hidden state E Çilden, F Polat 2013 IEEE 25th International Conference on Tools with Artificial …, 2013 | 6 | 2013 |
| 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 | 5 | 2023 |
| 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 |
| A configurable gateway for DDS-HLA interoperability MC Kaya, A Karamanlioglu, İÇ Çetintaş, E Çilden, H Canberi, ... Proceedings of the 2019 Summer Simulation Conference, 1-11, 2019 | 5 | 2019 |
| A generic distributed architecture to integrate simulated participants with modular avionics E Cilden, E Gültekin, D Poyraz, MH Canberi 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and …, 2018 | 5 | 2018 |
| 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 | 5 | 2016 |
| 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 |
| Abstraction in model based partially observable reinforcement learning using extended sequence trees E Cilden, F Polat 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and …, 2012 | 4 | 2012 |
| Generating effective initiation sets for subgoal-driven options A Demir, E Cilden, F Polat Advances in Complex Systems 22 (02), 1950001, 2019 | 3 | 2019 |
| A literature survey on DDS-HLA interoperability approaches MÇ Kaya, E Çilden, H Canberi, H Oğuztüzün USMOS, 2017 | 3 | 2017 |
| Abstraction in reinforcement learning in partially observable environments E Çilden Middle East Technical University, 2014 | 2 | 2014 |
| Data interoperability between DDS and HLA through a dynamically reconfigurable gateway MC Kaya, E Cilden, A Karamanlioglu, F Murat, AH Dogru, H Oguztuzun Software: Practice and Experience 53 (11), 2200-2221, 2023 | 1 | 2023 |
| 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 |
| Network packet loss sensitivity analysis for sympes codec E Ceran, E Çilden, E Gültekin, MH Canberi 2018 26th Signal Processing and Communications Applications Conference (SIU …, 2018 | 1 | 2018 |
| Using Transitional Bottlenecks to Improve Learning in Nearest Sequence Memory Algorithm H Aydın, E Cilden, F Polat 2017 IEEE 29th International Conference on Tools with Artificial …, 2017 | 1 | 2017 |
| Memory efficient factored abstraction for reinforcement learning C Şahin, E Çilden, F Polat 2015 IEEE 2nd International Conference on Cybernetics (CYBCONF), 18-23, 2015 | 1 | 2015 |
| Employing Automatic Temporal Abstractions to Accelerate Utile Suffix Memory Algorithm E Çilden, F Polat Multiagent System Technologies: 12th German Conference, MATES 2014 …, 2014 | 1 | 2014 |
Alper Demirİzmir University of Economics, University of EdinburghVerified email at ieu.edu.tr
