Ozgur S. Oguz

bio_oz.webp

I’m an Asst. Prof. in the area of AI & Robotics at Bilkent University and the lead of the Learning for Intelligent Robotic Agents (LiRA) Lab in the Dept. of Computer Engineering.

In my research, I focus on algorithms that can enrich the skill set of autonomous agents. This entails endowing intelligent systems with effective learning, reasoning, and planning capabilities. Robotics, and a range of other domains that require autonomous decision-making, provide a perfect test-bed for the investigation and application of such methods.

Prior to joining Bilkent U., I was a postdoctoral researcher at the Learning and Intelligence Systems Lab working with Marc Toussaint. I was affiliated with Uni Stuttgart & Max Planck Institute for Intelligent Systems, and working within the Cluster of Excellence: IntCDC. I received my PhD degree from TU Munich, where I focused on HRI in close-proximity scenarios. I studied computer science at UBC and Koç Uni.

available positions

  • Post-doc position is available
  • Motivated graduate / undergraduate students wanted. Contact me if you are interested in deep learning, (deep) perception, robotics, in general any topics in artificial intelligence. !!!

news

Sep 28, 2024 Our work Diffusion-based Curriculum Reinforcement Learning got accepted for NeurIPS’24. pdf
Sep 15, 2024 24-Fall: CS 449 / 549: Learning for Robotics course - Moodle
Sep 15, 2024 24-Fall: CS 461: Artificial Intelligence course - Moodle
Jun 13, 2024 Our preprint (on Deep Reinforcement Learning) is out CUER: Corrected Uniform Experience Replay for Off-Policy Continuous Deep Reinforcement Learning Algorithms - pdf.
May 01, 2024 Our work on Deep RL, Contact Energy Based Hindsight Experience Prioritization, got accepted for IEEE ICRA’24 - pdf.

selected publications

  1. 22-braun-IROS
    RHH-LGP: Receding Horizon And Heuristics-Based Logic-Geometric Programming For Task And Motion Planning
    Cornelius V. Braun, Joaquim Ortiz-Haro, Marc Toussaint, and 1 more author
    In IEEE IROS, 2022
  2. 22-hartmann-TRO
    Long-Horizon Multi-Robot Rearrangement Planning for Construction Assembly
    Valentin Noah Hartmann, Andreas Orthey, Danny Driess, and 2 more authors
    IEEE TRO - Transactions on Robotics, 2022
  3. 21-schubert-NeurIPS
    Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics
    Ingmar Schubert,  Driess, Danny, Ozgur S. Oguz, and 1 more author
    NeurIPS - Conf. on Neural Information Processing Systems, 2021