| 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 | 8 | 2019 |
| Local roots: A tree-based subgoal discovery method to accelerate reinforcement learning A Demir, E Çilden, F Polat Joint European conference on machine learning and knowledge discovery in …, 2016 | 8 | 2016 |
| 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 |
| 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 | 3 | 2017 |
| Automatic landmark discovery for learning agents under partial observability A Demіr, E Çіlden, F Polat The Knowledge Engineering Review 34, 2019 | 2 | 2019 |
| Learning What to Memorize: Using Intrinsic Motivation to Form Useful Memory in Partially Observable Reinforcement Learning A Demir arXiv preprint arXiv:2110.12810, 2021 | | 2021 |
| 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
