New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

loss function in mario_curio.py #25

Open

osm040836 opened this issue Aug 21, 2024 · 0 comments

osm040836 commented Aug 21, 2024

안녕하세요, mario_curio.py 파일에서 의문점이 들어 issue 남깁니다.
Line 277번째 줄에서 다음과 같이 entropy loss 항이 추가되어 계산되어야 하지 않나요?

기존) loss = (actor_loss + 0.5 * critic_loss) + icm_scale *
((1 - beta) * inverse_loss + beta * forward_loss)

변경) loss = (actor_loss + 0.5 * critic_loss - entropy_coef * entropy) + icm_scale *
((1 - beta) * inverse_loss + beta * forward_loss)'

감사합니다.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment