Machine Learning Researcher, PhD in Machine Learning. Been at @UCL @GoogleDeepmind @UCBerkeley ✨Researching Reinforcement Learning ✨Website: https://ezgikorkmaz.github.io/https://bsky.app/profile/ezgikorkmaz.bsky.socialhttps://bsky.app/profile/ezgikorkmaz.bsky.social/post/3mlo6b6db6k2a✨My single author paper just got accepted as a spotlight presentation at ICML 2026. Truly excited! More news to come! #ICML2026 @icmlconf.bsky.social12 May 2026 16:07 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3mlo6b6db6k2ahttps://bsky.app/profile/ezgikorkmaz.bsky.social/post/3mkalyxtbr22h✨Two single author papers accepted to ICLR 2026 ✨ Excited to share these results at #ICLR2026! @iclr-conf.bsky.social24 Apr 2026 13:10 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3mkalyxtbr22hhttps://bsky.app/profile/ezgikorkmaz.bsky.social/post/3mfp4dc736223✨Two single author papers accepted to ICLR 2026!✨ Truly excited to present these results at #ICLR2026 ! @iclr-conf.bsky.social #ICLR26 #DeepRL #ICLR #ReinforcementLearning25 Feb 2026 16:34 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3mfp4dc736223https://bsky.app/profile/ezgikorkmaz.bsky.social/post/3mdfq6vmdws2i✨Two of my single author papers just got accepted to #ICLR2026 ! Truly excited! More news to come! @iclr-conf.bsky.social27 Jan 2026 12:12 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3mdfq6vmdws2ihttps://bsky.app/profile/ezgikorkmaz.bsky.social/post/3mdeifrimzs26If you are interested in reinforcement learning or reinforcement learning training of language models, this might spark your interest! ✨See my new paper on scaling, capacity and complexity of reinforcement learning published at #AAAI2026 ! @aaai.org #AAAI #AAAI26 #ReinforcementLearning #DeepRL27 Jan 2026 00:20 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3mdeifrimzs26https://bsky.app/profile/ezgikorkmaz.bsky.social/post/3mcx2bfej5s2b✨Excited to present these results at #AAAI2026 ! 📜It is a must read if you are interested in reinforcement learning 📜 @aaai.org Paper: Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms #ReinforcementLearning #AAAI #AAAI26 #DeepRL21 Jan 2026 16:02 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3mcx2bfej5s2bhttps://bsky.app/profile/ezgikorkmaz.bsky.social/post/3m6mb7r3le227Excited to present these results at #NeurIPS2025! ✨My new paper on core principles of reinforcement learning was accepted as a Spotlight presentation at @neuripsconf.bsky.social !✨27 Nov 2025 11:27 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3m6mb7r3le227https://bsky.app/profile/ezgikorkmaz.bsky.social/post/3lm5zoqtay22dI opened this poll and I will share the results here as well: #ICML #ICML202506 Apr 2025 18:01 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3lm5zoqtay22dhttps://bsky.app/profile/ezgikorkmaz.bsky.social/post/3lhwaaewuh22aIf you are interested in large language models see my paper below on how we can uncover the biases learned by these models. Link: https://neurips2023-enlsp.github.io/papers/paper_95.pdf #ReinforcementLearning #FoundationModels #DeepRL #DeepReinforcementLearning #ResponsibleAI #AIBias #LLMs #LanguageModels11 Feb 2025 17:56 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3lhwaaewuh22ahttps://bsky.app/profile/ezgikorkmaz.bsky.social/post/3lh6ye5sqxk2gGave a lecture on Hoeffding's Inequality recently at #LMUMunich! Nice to have a chance to talk about foundations. Find my slides below: Link: ezgikorkmaz.github.io #Statistics #Probability #LMU #MachineLearning https://ezgikorkmaz.github.io02 Feb 2025 12:04 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3lh6ye5sqxk2ghttps://bsky.app/profile/ezgikorkmaz.bsky.social/post/3lgdqdidp5k2tIf you are interested in deep reinforcement learning, I will share this repo here: Link: https://github.com/EzgiKorkmaz/adversarial-reinforcement-learning #ReinforcementLearning #SafeAI #Adversarial #Robust #DeepRL #robustRL #LanguageModels #AdversarialRL #AISafety #ExplainableAI #TrustworthyAI #ResponsibleAI #DeepReinforcementLearning22 Jan 2025 15:59 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3lgdqdidp5k2thttps://bsky.app/profile/ezgikorkmaz.bsky.social/post/3lfpgsrn6sc2mA recent paper I wrote introduces foundational analysis on deep reinforcement learning decision making and representations learnt by it. Link: https://proceedings.mlr.press/v235/korkmaz24a.html #ReinforcementLearning #ICLR2025 #ACL2025 #NAACL2025 #NeurIPS2024 #ICML2025 #DeepRL #DeepReinforcementLearning14 Jan 2025 14:15 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3lfpgsrn6sc2mhttps://bsky.app/profile/ezgikorkmaz.bsky.social/post/3lfkmvsxor22bI wrote a recent survey about deep reinforcement learning. The paper is a compact guide to understand some of the key concepts in reinforcement learning. Link: https://arxiv.org/pdf/2401.02349v2 #ReinforcementLearning #ICLR2025 #ACL2025 #NAACL2025 #NeurIPS2024 #ICML2025 #DeepRL #DeepReinforcementLearning12 Jan 2025 16:21 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3lfkmvsxor22bhttps://bsky.app/profile/ezgikorkmaz.bsky.social/post/3lcxuz5ymek26The recent paper I wrote on deep reinforcement learning and generalization will appear #NeurIPS2024 @neuripsconf.bsky.social ! #ReinforcementLearning #DeepReinforcementLearning10 Dec 2024 18:35 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3lcxuz5ymek26https://bsky.app/profile/ezgikorkmaz.bsky.social/post/3lcpojz2aek2fIf you are curious about deep reinforcement learning find the compact highlights of my recent papers in this new short piece: #NeurIPS2024 @neuripsconf.bsky.social #NeurIPS24 #reinforcementlearning #AIsafety #AISecurity #ResponsibleAI #TrustworthyAI #RobustAI #DeepRL https://bsky.app/profile/ezgikorkmaz.bsky.social/post/3lclqpgignc2q [contains quote post or other embedded content]07 Dec 2024 12:18 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3lcpojz2aek2fhttps://bsky.app/profile/ezgikorkmaz.bsky.social/post/3lclqpgignc2qThe paper on adversarial non-robustness is now online! This paper highlights what you should now about Robust Reinforcement Learning. Adversarial Robust Deep Reinforcement Learning is Neither Robust Nor Safe Link: https://openreview.net/pdf?id=EPa0udvXJE #NeurIPS2024 neuripsconf.bsky.social #NeurIPS2405 Dec 2024 22:46 +0000at://did:plc:ao7h7cm6slhpogmkoircj2ih/app.bsky.feed.post/3lclqpgignc2q