Deep Learning: Train Network to "Play Game"
5 views (last 30 days)
Show older comments
M1997
on 3 Jun 2019
Answered: Gabija Marsalkaite
on 18 Jun 2019
My idea is to train a network so that the network can perform similarly to human subjects when playing a simple "game" eg. tracking an on screen cursor with computer mouse. The goal would be to train the network on human subjects' input/output data and then have it "play the game" and achieve similar output results. Ideally the network would have similar success and failure rates as the human subjects. Is this possible with Matlab's Deep Learning Toolbox or the Statistics and Machine Learning Toolbox? Thank you in advance!
0 Comments
Accepted Answer
Gabija Marsalkaite
on 18 Jun 2019
Hi Michael,
This strongly depends on how you want to implement it. Deep learning alone is most often used for tasks with labeled data (e.g. pictures of cats and dogs with corresponding labels) so if you have a labeled set of samples that might be a good idea (e.g. pictures of screen as samples and direction of movement as labels). Alternative to that is using reinforcement learning where agent learns by performing some action and then receiving a reward according to some quality of action metric (e.g. movement performed by agent is an action and reward is calculated by how close it is to the target). The plus of reinforcement learning that one does not have to create labels in advance but negative is that occasional it is difficult to define the best function describing the quality of an action.
0 Comments
More Answers (0)
See Also
Categories
Find more on Image Data Workflows in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!