Closed sandhawalia closed 4 years ago
Currently we include null_state to infer terminal or game over state. This can be factored out by using (1 - done) * gamma * Q
null_state
terminal
game over
(1 - done) * gamma * Q
addressed https://github.com/moabitcoin/cherry-pytorch/pull/9.
Currently we include
null_state
to inferterminal
orgame over
state. This can be factored out by using(1 - done) * gamma * Q