TD3 algorithm structure. by Hasan Raza Khanzada (22404835)

“…Five prominent RL algorithms that include Deep Deterministic Policy Gradient (DDPG), Twin Delayed Deep Deterministic Policy Gradient (TD3), Proximal Policy Optimization (PPO), Trust Region Policy Optimization (TRPO) and Soft Actor-Critic (SAC) are evaluated to determine their suitability for complex UAV flight dynamics, while highlighting their relative strengths and limitations. …”

TD3 algorithm. by Ahmed M. Hassan (8893106)

“…This paper proposes a new reinforcement learning (RL) control algorithm based twin-delayed deep deterministic policy gradient (TD3) algorithm to tune two cascaded PI controllers in a five-phase interior permanent magnet synchronous motor (5ph-IPMSM) drive system based model predictive control (MPC). …”

The Heading Control (left) and Roll Control (right) obtained on TD3 agent. by Hasan Raza Khanzada (22404835)

The Altitude Control (left) and Training Curve (right) obtained on TD3 agent. by Hasan Raza Khanzada (22404835)

Parameters for TD3 approach [60]. by Ahmed M. Hassan (8893106)

“…This paper proposes a new reinforcement learning (RL) control algorithm based twin-delayed deep deterministic policy gradient (TD3) algorithm to tune two cascaded PI controllers in a five-phase interior permanent magnet synchronous motor (5ph-IPMSM) drive system based model predictive control (MPC). …”

Dataset for Fine-Tuning Code Generation Models: Kannada-English Algorithmic Statements and Python Code by Goutami Sooda (20714729)

Convergence plots of the A-FedSAM algorithm and baseline algorithms under independent and identically distributed (IID) settings with 40% and 80% participation on the SPORT1 and SP... by Kexin Zhen (22453814)

Generated samples from experiment with 3 clients. by Hassan Kamran (21782056)

Generated Samples from experiment with 7 clients. by Hassan Kamran (21782056)

Generated samples from experiment with 5 clients. by Hassan Kamran (21782056)

Convergence plot of A-FedSAM and baseline algorithms under various settings on the SPORT2 dataset. by Kexin Zhen (22453814)

Convergence plot of A-FedSAM and baseline algorithms under various settings on the SPORT1 dataset. by Kexin Zhen (22453814)

Qualitative_Taguette analysis of all HCW and Clients. by Sani Useni (17804366)

Subjects:

Data and code resources. by Sam Hall-McMaster (10343795)

The multi-round test accuracy of A-FedSAM and baseline algorithms on the SPORT1 and SPORT2 datasets and 40% participation is reported as the mean ± variance. by Kexin Zhen (22453814)

The multi-round test accuracy of A-FedSAM and baseline algorithms on the SPORT1 and SPORT2 datasets and 80% participation is reported as the mean ± variance. by Kexin Zhen (22453814)

The multi-round test accuracy of A-FedSAM and baseline algorithms on the CIFAR-10/100, Tiny-ImageNet and AG-News datasets and 10% participation is reported as the mean ± variance. by Kexin Zhen (22453814)

The parameter setting of the evolutionary neural network. by Wenbing Shi (5806160)

Subjects:

The genome coding scheme. by Wenbing Shi (5806160)

Subjects:

The optimal number of clusters identified using the GMM clustering algorithm. by Dinh K. Tang (20469082)