| ||
News
|
||
ResearchI do research on reinforcement learning (RL), with a focus on generalization and adaptation. My publications can be found on my Google Scholar page, and some are listed with details below. During my research internship at HRI, I developed an action advising framework, Gen2Spec, that distills knowledge from generalist meta RL agents to specialists in a continual learning setting. Recently, I have been focusing on the following research directions:
Curriculum Learning for Reinforcement LearningThe design of task sequences, i.e., curricula, improves the performance of RL agents and speeds up the convergence in complex tasks. An effective curriculum typically begins with easy tasks and gradually changes them toward the target tasks. Common approaches require manually tailoring the curricula to identify easy and hard tasks, which requires domain knowledge that might be unavailable. My research focuses on developing automated curriculum generations algorithms that introduce a notion of risk, address constrained RL, and exploits task specifications.PublicationsCevahir Koprulu, Thiago D. Simão, Nils Jansen, Ufuk Topcu International Conference on Learning Representations (ICLR), 2025 Cevahir Koprulu, Thiago D. Simão, Nils Jansen, Ufuk Topcu Conference on Uncertainty in Artifical Intelligence (UAI), 2023 Cevahir Koprulu, Ufuk Topcu Conference on Uncertainty in Artifical Intelligence (UAI), 2023 Cevahir Koprulu, Ufuk Topcu International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023 (accepted as Extended Abstract) WorkshopsCevahir Koprulu, Thiago D. Simão, Nils Jansen, Ufuk Topcu RLBRew and RLSW at Reinforcement Learning Conference , 2024 Learning Reward Machines and PoliciesWe study the problem of reinforcement learning for a task encoded by a reward machine. The task is defined over a set of properties in the environment, called atomic propositions, and represented by Boolean variables. One unrealistic assumption commonly used in the literature is that the truth values of these propositions are accurately known. In real situations, however, these truth values are uncertain since they come from sensors that suffer from imperfections. At the same time, reward machines can be difficult to model explicitly, especially when they encode complicated tasks. We develop a reinforcement-learning algorithm that infers a reward machine that encodes the underlying task while learning how to execute it, despite the uncertainties of the propositions' truth values.PublicationsChristos Verginis, Cevahir Koprulu, Sandeep Chinchali, Ufuk Topcu Aritificial Intelligence, 2024 Level-k Game Theory to Model Human DriversLevel-k game theory is a hierarchical multi-agent decision-making model where a level-k player is a best responder to a level-(k-1) player. In this work, we studied level-k game theory to model reasoning levels of human drivers. Different from existing methods, we proposed a dynamic approach, where the actions are the levels themselves, resulting in a dynamic behavior. The agent adapts to its environment by exploiting different behavior models as available moves to choose from, depending on the requirements of the traffic situation.PublicationsCevahir Koprulu, Yildiray Yildiz IEEE Conference on Control Technology and Applications (CCTA), 2021 Cevahir Koprulu, Yildiray Yildiz ArXiV, 2021 |
This website is based on Jon Barron's source code.
His website can be found here.
|