activity
20242026
collaborators
Showing math.OCShow all

6 papers · 1 filter

math.OC2026

Preference-Based Reward Learning under Partial Observability with Inexact Dynamics

Reza Zolnouri, Semih Cayci

In this paper, we study how partial observability and inexact latent-state inference affect reward learning from preferences. To that end, we study preference-based reward learning…

math.OC2025

A Riemannian Optimization Perspective of the Gauss-Newton Method for Feedforward Neural Networks

Semih Cayci

In this work, we establish non-asymptotic convergence bounds for the Gauss-Newton method in training neural networks with smooth activations. In the underparameterized regime, the…

math.OC2025

Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes

Johannes Müller, Semih Cayci

We study the error introduced by entropy regularization in infinite-horizon discrete discounted Markov decision processes. We show that this error decreases exponentially in the in…

math.OC2025

Recurrent Natural Policy Gradient for POMDPs

Semih Cayci, Atilla Eryilmaz

Solving partially observable Markov decision processes (POMDPs) remains a fundamental challenge in reinforcement learning (RL), primarily due to the curse of dimensionality induced…

math.OC2025

Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients

Johannes Müller, Semih Çaycı, Guido Montúfar

Kakade's natural policy gradient method has been studied extensively in recent years, showing linear convergence with and without regularization. We study another natural gradient…

math.OC2025

A Variational Inequality Approach to Independent Learning in Static Mean-Field Games

Batuhan Yardim, Semih Cayci, Niao He

Competitive games involving thousands or even millions of players are prevalent in real-world contexts, such as transportation, communications, and computer networks. However, lear…