bad performance not like the paper
nguyenviettuan96 opened this issue · comments
The paper I read represents the result is very good convergence, but when I train using your code (not change anything), the model not converage and so result's chart is up and down, chaotic. Could you explaine that, please?
@nguyenviettuan96 Thanks for asking. The environment and RL implementation have been updated with multiple iterations. So the results are not comparable. But You should be able to see similar trends.
I've tried changing the parameters and let it run for more iterations , but it doesn't converge at all and I couldn't see a similar trend. what would be the possible issues?