I do not get the idea of you using memory capacity greater that T_MAX. Shouldn't the implementation have memory capacity be less than the T_MAX. This looks more intuitive to me. Please let me know what do you think.
You're right, there's no point to having the memory capacity be greater than the number of samples it could ever receive. Fixed to something perhaps more reasonable.
https://github.com/Kaixhin/ACER/blob/5b7ca5d75bf16629ddaf68ecab4ab6c7dcccf56c/main.py#L25
Hello Kaixhin,
I do not get the idea of you using memory capacity greater that T_MAX. Shouldn't the implementation have memory capacity be less than the T_MAX. This looks more intuitive to me. Please let me know what do you think.