Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

RL expert here, the problem with vision is that most likely, it takes too long to render and to process the render in your NN.

At that point you need to run the game real-time instead of faster, so you need a lot of compute to generate your data. You will also need the bandwidth to throw the data around, and the GPUs to take all that input size.

It's definitely possible, but not the place to start, and will require a lot more compute infrastructure.



I’m not saying render the scene. I’m saying take your measurements from where the camera is (or would be).

It would require no extra infra or compute.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: