News for hackers. Stuff that matters.
Re:Why traditional reinforcement learning will probably not ... by Animats on Wednesday October 21, 2020 @09:03PM (#24853952)
That an AGI must be capable of performing optimally on a task with Archimedean measure.

If that's correct, this may be just one of those many problems where the optimal solution is far harder than a near-optimal solution. Examples include linear programming and the traveling salesman problem, where a true optimum is NP-hard to find, but you can get very close with far less work.

There are no comments on this comment yet.