Yiğit Yalın — accepted AI-conference papers

2026

Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks

Paulius Sasnauskas, Yiğit Yalın, Goran Radanovic

ICML 2026poster

We study the corruption-robustness of in-context reinforcement learning (ICRL), focusing on the Decision-Pretrained Transformer (DPT, Lee et al., 2023). To address the challenge of reward poisoning attacks targeting the DPT, we propose a novel adversarial training framework, called Adversarially Tra…

Cited by 0 Source ↗Scholar ↗

2025

Independent Learning in Performative Markov Potential Games

Rilind Sahitaj, Paulius Sasnauskas, Yiğit Yalın, Debmalya Mandal, Goran Radanovic

AISTATS 2025poster

Performative Reinforcement Learning (PRL) refers to a scenario in which the deployed policy changes the reward and transition dynamics of the underlying environment. In this work, we study multi-agent PRL by incorporating performative effects into Markov Potential Games (MPGs). We introduce the not…

Cited by 0 Source ↗code ↗Scholar ↗