collaborators

14 papers

cs.LG2026

Policy-based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards

Orhun Bugra Baran, Melih Kandemir, Ramazan Gokberk Cinbis

Autoregressive (AR) models are highly effective for image generation, yet their standard maximum-likelihood estimation training lacks direct optimization for sample quality and div…

cs.LG2026

Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies

Magnus Victor Boock, Abdullah Akgül, Mustafa Mert Çelikok +1

We present a new operator-theoretic representation learning framework for offline reinforcement learning that recovers the directed temporal geometry of a controlled Markov process…

cs.LG2026

A Measure-Theoretic Finite-Sample Theory for Adaptive-Data Fitted Q-Iteration

Manuel Haussmann, Mustafa Mert Çelikok, Melih Kandemir

While reinforcement learning (RL) promises to revolutionize the control of complex nonlinear robotic systems, a profound gap persists between the heuristic success of model-free of…

cs.LG2026

Adaptive Ensemble Aggregation for Actor-Critics

Nicklas Werge, Yi-Shan Wu, Manuel Haussmann +2

Ensembles are ubiquitous in off-policy actor-critic learning, yet their efficacy depends critically on how they are aggregated. Current methods typically rely on static rules or ta…

cs.LG2026

Distributional Active Inference

Abdullah Akgül, Abdullah Akgül, Gulcin Baykal +5

Optimal control of complex environments with robotic systems faces two complementary and intertwined challenges: efficient organization of sensory state information and far-sighted…

cs.LG2025

Deep Actor-Critics with Tight Risk Certificates

Bahareh Tasdighi, Manuel Haussmann, Yi-Shan Wu +2

Deep actor-critic algorithms have reached a level where they influence everyday life. They are a driving force behind continual improvement of large language models through user fe…