Abdullah Akgül

According to our database, Abdullah Akgül authored at least 14 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of five.

2026

Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies.

Magnus Victor Boock, Abdullah Akgül, Mustafa Mert Çelikok, Melih Kandemir

CoRR, May, 2026

Distributional Active Inference.

Abdullah Akgül, Gulcin Baykal, Manuel Haußmann, Mustafa Mert Çelikok, Melih Kandemir

CoRR, January, 2026

2025

ObjectRL: An Object-Oriented Reinforcement Learning Codebase.

Gulcin Baykal, Abdullah Akgül, Manuel Haussmann, Bahareh Tasdighi, Nicklas Werge, Yi-Shan Wu, Melih Kandemir

CoRR, July, 2025

Improving Plasticity in Non-stationary Reinforcement Learning with Evidential Proximal Policy Optimization.

Abdullah Akgül, Gulcin Baykal, Manuel Haußmann, Melih Kandemir

CoRR, March, 2025

Overcoming Non-stationary Dynamics with Evidential Proximal Policy Optimization.

Abdullah Akgül, Gulcin Baykal, Manuel Haussmann, Melih Kandemir

Trans. Mach. Learn. Res., 2025

2024

Calibrating Bayesian UNet++ for Sub-Seasonal Forecasting.

Busra Asan, Abdullah Akgül, Alper Ünal, Melih Kandemir, Gozde Unal

CoRR, 2024

Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning.

Abdullah Akgül, Manuel Haussmann, Melih Kandemir

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Continual learning of multi-modal dynamics with external memory.

Abdullah Akgül, Gozde Unal, Melih Kandemir

Proceedings of the 6th Annual Learning for Dynamics & Control Conference, 2024

PAC-Bayesian Soft Actor-Critic Learning.

Bahareh Tasdighi, Abdullah Akgül, Manuel Haussmann, Kenny Kazimirzak Brink, Melih Kandemir

Proceedings of the Symposium on Advances in Approximate Bayesian Inference, 2024

2023

Meta Continual Learning on Graphs with Experience Replay.

Altay Unal, Abdullah Akgül, Melih Kandemir, Gozde Unal

Trans. Mach. Learn. Res., 2023

BOF-UCB: A Bayesian-Optimistic Frequentist Algorithm for Non-Stationary Contextual Bandits.

Nicklas Werge, Abdullah Akgül, Melih Kandemir

CoRR, 2023

PAC-Bayesian Soft Actor-Critic Learning.

Bahareh Tasdighi, Abdullah Akgül, Kenny Kazimirzak Brink, Melih Kandemir

CoRR, 2023

2022

How to Combine Variational Bayesian Networks in Federated Learning.

Atahan Ozer, Kadir Burak Buldu, Abdullah Akgül, Gozde Unal

CoRR, 2022

Evidential Turing Processes.

Melih Kandemir, Abdullah Akgül, Manuel Haußmann, Gozde Unal

Proceedings of the Tenth International Conference on Learning Representations, 2022