3 papers
cs.LG2025
An Integrated Approach to Neural Architecture Search for Deep Q-Networks
Iman Rahmani, Saman Yazdannik, Morteza Tayefi +1
The performance of deep reinforcement learning agents is fundamentally constrained by their neural network architecture, a choice traditionally made through expensive hyperparamete…
cs.LG2025
Beyond ReLU: Chebyshev-DQN for Enhanced Deep Q-Networks
Saman Yazdannik, Morteza Tayefi, Shamim Sanisales
The performance of Deep Q-Networks (DQN) is critically dependent on the ability of its underlying neural network to accurately approximate the action-value function. Standard funct…
cs.LG2023
Nonlinear System Identification of Swarm of UAVs Using Deep Learning Methods
Saman Yazdannik, Morteza Tayefi, Mojtaba Farrokh
This study designs and evaluates multiple nonlinear system identification techniques for modeling the UAV swarm system in planar space. learning methods such as RNNs, CNNs, and Neu…