Live data from Hacker News

SafeLife: AI Safety Environments Based on Conway's Game of Life

partnershiponai.org

11–13 of 13 posts

Re: SafeLife: AI Safety Environments Based on Conway's Game of Life

#11
post #5

May be useful, but it seems to me that the reward function still is relatively easy to specify? Much of the difficulty in AI safety is due to specify what humans really want. Perhaps the AI can observe a human playing the game and learn a reward function?

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 of Life

#12
post #2

With some graphics this looks like it could be a rather fun game to play manually. I wonder if there is such a thing? Maybe multiplayer support as well?

Right in the readme it describes how to launch interactively via `safelife play puzzles`

Yes but it’s missing decent graphics, sounds, animations, imagination... etc

Re: SafeLife: AI Safety Environments Based on Conway's Game of Life

#13
Hasn't Conway himself been known to say that he don't like the Game of Life since it doesn't give rise to that many interesting mathematical conclusions and how everybody is focusing on it above some of his other math axhievments? Maybe finally he can find the use case he wanted for it. And maybe it also gives reason to all the hours people have spent researching and finding new structures in Game of Life.
Post reply on HN