On: Where machine learning meets rule-based systems

[cbames89]

"Training it to mimic humans means it will always be worse than humans." This is not necessarily true, there is work in learning from demonstration where robots have exceed the "experts" reward. I'll post some papers later if you're interested.

[YeGoblynQueenne → cbames89]

Please do. I'm not the OP but I'm interested.

[cbames89 → YeGoblynQueenne]

Sorry for the delay. Here's some early work from Pieter Abbeel where a helicopter does aerobatic manuevers better than the demonstrations it received: http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=EAE...