Comment by wetpaws 8 years ago Whatever the reward function dictates would be a win :) 1 comment wetpaws Reply ForHackernews 8 years ago Right. So we've just successfully moved the goalposts to "write a reward function that objectively evaluates g"
ForHackernews 8 years ago Right. So we've just successfully moved the goalposts to "write a reward function that objectively evaluates g"
Right. So we've just successfully moved the goalposts to "write a reward function that objectively evaluates g"