Every indexed document

or a robot that vacuums the living room rug while you’re at work

we’ve assumed that if we’re successful—if robots can

a robot’s job is to figure out what actions it should take in

and it incurs a small cost every time it moves; this reward function

we define a reward function—a mapping from states and

for instance. States are locations in the world

a good model of the Earth’s climate should be able to predict the

including circumstances unanticipated by its

a student might infer that his professor is indifferent to him if the

the statistician can then work backward: What rewards would likely

you infer that they must really like classical

inverse reinforcement learning is something people do all the

we can infer the rewards that led to the development of those

but the intervening decades have developed it into a fine

programmed with the exquisite skills needed to enact that

to burn people to death for being infidels

being content despite their lives of suffering and grueling labor and despite

learning at the feet of their elders to recite the tribal lore by

there were hundreds of thousands of years of near stasis.

it would also have been used for innovation