News for hackers. Stuff that matters.
Re:Reinforcement Learning with Prediction-Based Rewards by mooneater on Wednesday October 31, 2018 @03:20PM (#18348532)
If you read it thats exactly what they addressed here. They say they address the noisy TV problem. The video shows why they needed to address it.

> These choices make RND immune to the noisy-TV problem.

There are no comments on this comment yet.