publications | Melis Ilayda Bal

2025

ICLR 2025

Adversarial Training for Defense Against Label Poisoning Attacks

Melis Ilayda Bal, Volkan Cevher, and Michael Muehlebach

In International Conference on Learning Representations, 2025

Bib HTML

@article{mib-floral,
  author = {Bal, Melis Ilayda and Cevher, Volkan and Muehlebach, Michael},
  title = {Adversarial Training for Defense Against Label Poisoning Attacks},
  journal = {In International Conference on Learning Representations},
  year = {2025},
}

ICLR 2025

Optimistic Games for Combinatorial Bayesian Optimization with Applications to Protein Design

Melis Ilayda Bal, Pier G. Sessa, Mojmir Mutny, and Andreas Krause

In International Conference on Learning Representations, 2025

Preliminary version presented at NeurIPS 2023 ReALML Workshop, [Best paper award finalist*, Spotlight talk*]

Bib HTML

@article{mib-gameopt,
  author = {Bal, Melis Ilayda and Sessa, Pier G. and Mutny, Mojmir and Krause, Andreas},
  title = {Optimistic Games for Combinatorial Bayesian Optimization with Applications to Protein Design},
  journal = {In International Conference on Learning Representations},
  year = {2025},
  note = {Preliminary version presented at NeurIPS 2023 ReALML Workshop, [Best paper award finalist*, Spotlight talk*]},
}

2024

Population-based Exploration in Reinforcement Learning through Repulsive Reward Shaping Using Eligibility Traces

Melis Ilayda Bal, Huseyin Aydin, Cem Iyigun, and Faruk Polat

Annals of Operations Research, Jan 2024

Bib HTML

@article{mib-anor,
  author = {Bal, Melis Ilayda and Aydin, Huseyin and Iyigun, Cem and Polat, Faruk},
  title = {Population-based Exploration in Reinforcement Learning through Repulsive Reward Shaping Using Eligibility Traces},
  journal = {Annals of Operations Research},
  year = {2024},
  month = jan,
}

Potential-Based Reward Shaping Using State-Space Segmentation for Efficiency in Reinforcement Learning

Melis Ilayda Bal, Huseyin Aydin, Cem Iyigun, and Faruk Polat

Future Generation Computer Systems, Jan 2024

Bib HTML

@article{mib-fgcs,
  author = {Bal, Melis Ilayda and Aydin, Huseyin and Iyigun, Cem and Polat, Faruk},
  title = {Potential-Based Reward Shaping Using State-Space Segmentation for Efficiency in Reinforcement Learning},
  journal = {Future Generation Computer Systems},
  volume = {157},
  pages = {469-484},
  year = {2024},
  issn = {0167-739X},
  doi = {https://doi.org/10.1016/j.future.2024.03.057},
}

2023

NeurIPS 2023

Optimistic Games for Combinatorial Bayesian Optimization with Applications to Protein Design

Melis Ilayda Bal, Pier G. Sessa, Mojmir Mutny, and Andreas Krause

NeurIPS ReALML Workshop, Dec 2023

Best paper award finalist*, Spotlight talk*

Bib HTML

@article{mib-gameopt-preprint,
  author = {Bal, Melis Ilayda and Sessa, Pier G. and Mutny, Mojmir and Krause, Andreas},
  title = {Optimistic Games for Combinatorial Bayesian Optimization with Applications to Protein Design},
  journal = {NeurIPS ReALML Workshop},
  year = {2023},
  note = {Best paper award finalist*, Spotlight talk*},
  month = dec,
}

2022

MSc Thesis

Reward Shaping for Efficient Exploration and Acceleration of Learning in Reinforcement Learning

Melis Ilayda Bal

Jul 2022

M.S. - Master of Science

Bib HTML

@mastersthesis{mib-thesis,
  author = {Bal, Melis Ilayda},
  title = {Reward Shaping for Efficient Exploration and Acceleration of Learning in Reinforcement Learning},
  school = {Middle East Technical University},
  year = {2022},
  type = {M.S. - Master of Science},
  month = jul,
  note = {M.S. - Master of Science},
}