AI breaks the game of hide and seek

This is a really fun video where an AI is given a version of the game of hide and seek and each team has to learn ways to win - either by finding the other team or by not being found.

Over time they develop and adapt to each others strategies including having to work as a team to win. They also find ways to break the expected rules including finding actual issues with the modelling of the environment. Other approaches are just really clever ways to win - mostly on the hiding side but also occasionally from the seeking team. These are all beautifully and clearly illustrated in the video.

Links

OpenAI Plays Hide and Seekā€¦and Breaks The Game!

Random Posts

The loosely held product roadmap

In a recent article by Ryan Singer, Options, Not Roadmaps, he explains why he doesn’t use roadmaps - he uses options instead.


Read More

Openness, discussions and success

I work very closely with two colleagues - and have done so for a number of years. Together we have experienced some serious ups and downs in the company we work for and also personally. We have each reached a point where we were close to leaving; we have each had something happen in our lives where the others have supported us.


Read More

Git - what to do when it goes wrong

This has a great summary of what to do when things go wrong when using Git. Added here so I know where to look in moments of panic.


Read More