Re:SafeLife: AI Safety Environments Based on Conway's Game o...
by nopinsight on Thursday December 05, 2019 @09:42AM
(#21712588)
A subarea of AI research focused on learning the reward function is Inverse Reinforcement Learning. Here’s an article on it:
Learning from humans: what is inverse reinforcement learning? https://thegradient.pub/learning-from-humans-what-is-inverse...
Re:SafeLife: AI Safety Environments Based on Conway's Game o...
by pde3 on Thursday December 05, 2019 @05:31AM
(#21711295)
The problem is very easy to solve if the reward function (avoid altering the green life patterns) is specified. The aim in SafeLife version 1.0 (future versions will add more safety problems) is to find an agent/architecture that naturally has conservatism with respect to side effects, without being told which particular side effects in particular are bad.
Re:SafeLife: AI Safety Environments Based on Conway's Game o...
by petters on Thursday December 05, 2019 @09:32AM
(#21712504)
I see, thanks!
Re:SafeLife: AI Safety Environments Based on Conway's Game o...
by Jeff_Brown on Thursday December 05, 2019 @09:13AM
(#21712379)
> Much of the difficulty in AI safety is due to specify what humans really want.
Much of the difficulty of programming (for someone else) is due to the same thing.
Perhaps the AI can observe a human playing the game and learn a reward function?