DMTD algorithm. by Yunhu Huang (21402795)

“…On the basis of EITO_E, we propose EITO_P algorithm using the PPO algorithm to optimize multiple objectives by designing reinforcement learning strategies, rewards, and value functions. …”

Streamfunction calculated by QA with different with different grid resolutions Streamfunction averaged over 10 runs from QA (shading) and the “true” solution (black contour lines)... by Takuro Matsuta (21608505)

Fig 3 - by Ali Ahmed (2567584)

Binary leaf image rotated anti-clock wise from the origin degree to 40^<i>o</i>, 80^<i>o</i>, 120^<i>o</i>, and 160^<i>o</i> from left to ri... by Ali Ahmed (2567584)

Optimization framework. by Nisha Ann Viswan (20371285)

Gray variance product line chart. by Qianwei Deng (19353264)

EITO_P with flexible trip time. by Yunhu Huang (21402795)

“…On the basis of EITO_E, we propose EITO_P algorithm using the PPO algorithm to optimize multiple objectives by designing reinforcement learning strategies, rewards, and value functions. …”

Energy consumption in the PPO process. by Yunhu Huang (21402795)

“…On the basis of EITO_E, we propose EITO_P algorithm using the PPO algorithm to optimize multiple objectives by designing reinforcement learning strategies, rewards, and value functions. …”

Speed limits. by Yunhu Huang (21402795)

“…On the basis of EITO_E, we propose EITO_P algorithm using the PPO algorithm to optimize multiple objectives by designing reinforcement learning strategies, rewards, and value functions. …”

Running time in the PPO process. by Yunhu Huang (21402795)

“…On the basis of EITO_E, we propose EITO_P algorithm using the PPO algorithm to optimize multiple objectives by designing reinforcement learning strategies, rewards, and value functions. …”

Speed limits and gradients from RJ to WYJ. by Yunhu Huang (21402795)

“…On the basis of EITO_E, we propose EITO_P algorithm using the PPO algorithm to optimize multiple objectives by designing reinforcement learning strategies, rewards, and value functions. …”

EITO_E speed distance profile. by Yunhu Huang (21402795)

“…On the basis of EITO_E, we propose EITO_P algorithm using the PPO algorithm to optimize multiple objectives by designing reinforcement learning strategies, rewards, and value functions. …”

Speed limits and gradient from SJZ to XHM. by Yunhu Huang (21402795)

“…On the basis of EITO_E, we propose EITO_P algorithm using the PPO algorithm to optimize multiple objectives by designing reinforcement learning strategies, rewards, and value functions. …”

Parameters of DKZ32. by Yunhu Huang (21402795)

“…On the basis of EITO_E, we propose EITO_P algorithm using the PPO algorithm to optimize multiple objectives by designing reinforcement learning strategies, rewards, and value functions. …”

EITO_<i>P</i> with a variable trip time. by Yunhu Huang (21402795)

“…On the basis of EITO_E, we propose EITO_P algorithm using the PPO algorithm to optimize multiple objectives by designing reinforcement learning strategies, rewards, and value functions. …”

Streamfunction calculated by SA with different hyperparameters. by Takuro Matsuta (21608505)

SA solutions using a series of spins without iteration. by Takuro Matsuta (21608505)

QA solutions using a series of spins without iteration. by Takuro Matsuta (21608505)

QA and SA solutions by truncated spectral expansion when by Takuro Matsuta (21608505)

Schematic of <i>P. chabaudi</i> within-host infection dynamics and fitness optimization. by Avril Wang (22404300)

“…For local optimization, an arbitrary starting spline is picked (left panel) and an optimization algorithm is used to adjust the relative weights of the basis functions until a fitness maximum is achieved (going from left to right). …”