Research Interests

• Reinforcement Learning
• MDPs and POMDPs
• Machine Learning
• Data Science

Publications

• Demіr, Alper, Erkіn Çіlden, and Faruk Polat. "Automatic landmark discovery for learning agents under partial observability." The Knowledge Engineering Review 34, 2019.
• Demir, Alper, Erkin Çilden, and Faruk Polat. "Landmark Based Reward Shaping in Reinforcement Learning with Hidden States." Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems. International Foundation for Autonomous Agents and Multiagent Systems, 2019.
• Demi̇r, Alper, Erki̇n Çi̇lden, and Faruk Polat. "Generating Effective Initiation Sets For Subgoal-Driven Options." Advances in Complex Systems 22.02, 2019.
• Demir, Alper, Erkin Cilden, and Faruk Polat. "A concept filtering approach for diverse density to discover subgoals in reinforcement learning." 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2017.
• Demir, Alper, Erkin Çilden, and Faruk Polat. "Local roots: A tree-based subgoal discovery method to accelerate reinforcement learning." Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, Cham, 2016.
• Demir, Alper, Erkin Çilden, and Faruk Polat. "A history tree heuristic to generate better initiation sets for options in reinforcement learning." Proceedings of the Twenty-second European Conference on Artificial Intelligence, 2016.