????? ??????? ? ??????????? ???? ??? ????????????? ?????????? ?????? ???????????? ?????????? ???? ?????? ???? ????? ????? ??????? ?? ??? ?????? ????? ?? ????? ??????? ???? ???? ??? ???? ?? ?????????? ?????????? ????? ??????? ??? ????????? ?? ????????.??????? ??????? ?????? ????? ??????? ??? ??? ????? ???? ???????? ???? ???? ??? ?? ???? ???? ???? ??

“What Usually tends to happen with reinforcement Finding out, Just about whatever the technique, is that you get the policy that solves The actual occasion of the challenge you’ve been teaching on, but it surely doesn’t generalize,” mentioned Julian Togelius, a pc scientist at New York College and investigation director at modl.ai.Tom Zahav