Publications

Google Scholar

Preprints/Working Papers⌗

• Learning Task Representations from In-Context Learning,
  Baturay Saglam, Zhuoran Yang, Dionysis Kalogerias, Amin Karbasi
  Appeared in ICML 2024 Workshop on In-Context Learning.

• Compatible Gradient Approximations for Actor-Critic Algorithms,
  Baturay Saglam, Dionysis Kalogerias
  Appeared in ICML 2024 Workshop on Foundations of RL and Control.

Journal Articles⌗

• Mitigating Off-Policy Bias in Actor-Critic Methods with One-Step Q-learning: A Novel Correction Approach,
  Baturay Saglam, Dogan C. Cicek, Furkan B. Mutlu, Suleyman S. Kozat,
  Transactions of Machine Learning Research, 2024.

• Parameter-free Reduction of the Estimation Bias in Deep Reinforcement Learning for Deterministic Policy Gradients,
  Baturay Saglam, Furkan B. Mutlu, Dogan C. Cicek, Suleyman S. Kozat,
  Neural Processing Letters, 2024.

• Actor Prioritized Experience Replay,
  Baturay Saglam, Furkan B. Mutlu, Dogan C. Cicek, Suleyman S. Kozat,
  Journal of Artificial Intelligence Research, 2023.

• Deep Intrinsically Motivated Exploration in Continuous Control,
  Baturay Saglam, Suleyman S. Kozat,
  Machine Learning, 2023.  

Peer-Reviewed Conference Proceedings⌗

• User Feedback-based Online Learning for Intent Classification,
  Kaan Gonc, Baturay Saglam, Onat Dalmaz, Tolga Cukur, Serdar Kozat, Hamdi Dibeklioglu,
  ACM 25th International Conference on Multimodal Interaction, 2023.

• Deep Reinforcement Learning Based Joint Downlink Beamforming and RIS Configuration in RIS-aided MU-MISO Systems Under Hardware Impairments and Imperfect CSI,
  Baturay Saglam, Doga Gurgunoglu, Suleyman S. Kozat,
  IEEE International Conference on Communications Workshops, 2023.

• An Optimistic Approach to the Temporal Difference Error in Off-Policy Actor-Critic Algorithms,
  Baturay Saglam, Furkan B. Mutlu, Suleyman S. Kozat,
  IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, 2022.

• Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methods,
  Baturay Saglam, Enes Duran, Dogan C. Cicek, Furkan B. Mutlu, Suleyman S. Kozat,
  IEEE 33rd International Conference on Tools with Artificial Intelligence, 2021.

• AWD3: Dynamic Reduction of the Estimation Bias,
  Dogan C. Cicek, Enes Duran, Baturay Saglam, Kagan Kaya, Furkan B. Mutlu, Suleyman S. Kozat,
  IEEE 33rd International Conference on Tools with Artificial Intelligence, 2021.

• Off-Policy Correction for Deep Deterministic Policy Gradient Algorithms via Batch Prioritized Experience Replay,
  Dogan C. Cicek, Enes Duran, Baturay Saglam, Furkan B. Mutlu, Suleyman S. Kozat,
  IEEE 33rd International Conference on Tools with Artificial Intelligence, 2021.
   

Workshop Papers⌗

• Actor Prioritized Experience Replay,
  Baturay Saglam, Furkan B. Mutlu, Dogan C. Cicek, Suleyman Serdar Kozat,
  Deep Reinforcement Learning Workshop NeurIPS, 2022.

• Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms,
  Baturay Saglam, Dogan C. Cicek, Furkan B. Mutlu, Suleyman S. Kozat,
  ICML Workshop on Responsible Decision Making in Dynamic Environments, 2022.