Backend Developer (Python , Django, Flask )
set of agents capable of learning (optimally) COVID-19 mitigation policies was designed via the virl environment. The agents are divided into three methods to implement their effects, namely random agents, deterministic agents, and Q-learning with function approximately, after being disturbed is detected using noise and random. Observe the changes in reward, action, and state to select the best policy Link: https://colab.research.google.com/drive/1KYLEoJg3MtcVIk47HWZ6xzWGCQSbHaaQ?usp=sharing Sep– JunMobile network software and base station implementation via C++ Built on the Linux e...
A tiempo completo / Interesado en trabajar a distancia
University of Glasgow
Computer system engineering