Home
GoPark
UAV Q-Learn
TweetRank
Crowd Detection
Random Walk
Graphy
Densely
Close Menu
Open Menu
Projects
Home
Random Walk Simulation
Project Specifics
Name
Simulation using Reinforcement Learning
Academic Year
M.S. - 1st Year
Date
January 2018 - Present
Status
Ongoing
Github Link
Will Be Updated in March 2018
Technicalities:-
Reinforcement Learning; Modelling random walk; visualizing with OpenGL
Project Description
Ongoing Research. Details will be updated after completion.
Working with Dr. Orit Peleg in her lab PelegLab
(https://www.peleglab.com/)
. I am working on her Project “Optimal intermittent reorientation”.
Using Reinforcement Learning to learn from a biological agent and increase automatic vehicular navigation accuracy.
Data is being extracted from 20 hours worth of video.
This data will be used to train a neural netowrk.
The Neural Network and Reinforcement Learning models will be compared.
<