Research Themes on Kenshi Abehttps://bakanaouji.github.io/research/Recent content in Research Themes on Kenshi AbeHugo -- gohugo.ioen© 2026 Kenshi AbeBandits and Online Learninghttps://bakanaouji.github.io/research/bandits-online-learning/Mon, 01 Jan 0001 00:00:00 +0000https://bakanaouji.github.io/research/bandits-online-learning/How can agents learn efficiently while making decisions online?Fairness in Recommender Systems and Allocationhttps://bakanaouji.github.io/research/fairness-recsys-allocation/Mon, 01 Jan 0001 00:00:00 +0000https://bakanaouji.github.io/research/fairness-recsys-allocation/How can we allocate limited resources and opportunities fairly?Language Model Alignment and Preference Optimizationhttps://bakanaouji.github.io/research/language-model-alignment/Mon, 01 Jan 0001 00:00:00 +0000https://bakanaouji.github.io/research/language-model-alignment/How can we generate language model outputs that align with human preferences?Learning Dynamics and Equilibrium Computation in Gameshttps://bakanaouji.github.io/research/learning-dynamics-equilibrium-games/Mon, 01 Jan 0001 00:00:00 +0000https://bakanaouji.github.io/research/learning-dynamics-equilibrium-games/How can learning algorithms converge quickly to Nash equilibrium?Reinforcement Learning and Sequential Decision Makinghttps://bakanaouji.github.io/research/reinforcement-learning-sequential-decision/Mon, 01 Jan 0001 00:00:00 +0000https://bakanaouji.github.io/research/reinforcement-learning-sequential-decision/How can agents improve and evaluate policies over time?