Algorithm for optimal decision determination in sequential decision-making. by Mariko I. Ito (5007323)

Algorithm framework in revitalizing HBs. by Kailun Fang (13949729)

Mean scores of the last 100 episodes using PPO and DQN in Unity environment and ViZDoom. by Enoch Solomon (21416703)

Subjects:

Mean reward of using visual information, visual information with raw audio samples in Unity ML environment. by Enoch Solomon (21416703)

Subjects:

Proposed reinforcement learning architecture. by Enoch Solomon (21416703)

Subjects:

The scenario used in Unity environment. Both the agent and target are spawned randomly at the start of the game anywhere in the game environment for each episode. by Enoch Solomon (21416703)

Subjects:

The images shown correspond the downscaled images an agent receives in Unity environment. by Enoch Solomon (21416703)

Subjects:

Mean reward of using only pixels and pixels with raw audio samples in ViZDoom environment. by Enoch Solomon (21416703)

Subjects:

The mean and standard deviation of the test results are presented for the use of both visual information and raw audio samples in the Unity ML environment. by Enoch Solomon (21416703)

Subjects:

Average success rate (%) of the test experiment on ViZDoom and Unity environments. by Enoch Solomon (21416703)

Subjects:

The mean reward results of using visual information and audio samples in the ViZDoom environment. by Enoch Solomon (21416703)

Subjects:

Box plot of Unity ML experiments using visual information, audio samples and combination of visual information and audio samples. by Enoch Solomon (21416703)

Subjects:

Study case/patient distribution algorithm. by Navid Behzadi Koochnai (18554931)