New Preprints
S. Cayci and A. Eryilmaz, Recurrent Natural Policy Gradient for POMDPs, arXiv preprint: 2405.18221, 2024.S. Cayci and A. Eryilmaz, Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis, arXiv preprint: 2402.12241, 2024.
Selected Publications
S. Cayci, N. He, R. Srikant, Convergence of entropy-regularized natural policy gradient with linear function approximation, SIAM Journal on Optimization 34.3, 2729-2755, 2024.S. Cayci, N. He, R. Srikant, Finite-time analysis of entropy-regularized neural natural actor-critic algorithm, Transactions of Machine Learning Research, 2024.S. Cayci, N. He, R. Srikant, Finite-time analysis of natural actor-critic for POMDPs, SIAM Journal on Mathematics of Data Science, 6.4, 869-896, 2024.S. Cayci and A. Eryilmaz, Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards, NeurIPS 2023.S. Cayci, S. Satpathi, N. He, R. Srikant, Sample Complexity and Overparameterization Bounds for Temporal Difference Learning with Neural Network Approximation, IEEE Transactions on Automatic Control, 2023.B. Yardim, S. Cayci, M. Geist, N. He, Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games, ICML 2023.
