News for hackers. Stuff that matters.
Re:Deep reinforcement learning is a waste of time (2019) by MathYouF on Saturday July 10, 2021 @02:54PM (#27795582)
Dogs have achieved an unbroken chain of survival dating back as far as your ancestors have, so they've achieved the same survival goals as you.

They've managed to do so without our intellectual abilities, which goes to prove that our goals of making RL algorithms become "smart" is malformed since high level complex and abstract reasoning skills apparently aren't a necessarily prerequisite to survival, at least in our earth environment.

Re:Deep reinforcement learning is a waste of time (2019) by cma on Saturday July 10, 2021 @03:19PM (#27795752)
Worker ants end the chain of survival, but are still necessary, so chain of surival among individuals is a flawed metric.
Re:Deep reinforcement learning is a waste of time (2019) by MathYouF on Saturday July 10, 2021 @03:43PM (#27795909)
Indeed, the genetics of every living thing are not evidence of its fitness, but once it has reproduced, it is.