Inquiry regarding your paper and its implementation

[songsang7]

Dear Author,

I read your paper with great interest and appreciate you sharing the code.
I have a question regarding the implementation:

1. In LAP (for priority updates) and PAL (for lambda calculation), why is a max operation used among td-errors, rather than mean or min?
   

I would appreciate your clarification on this point.

Thank you for your time and research.

Sincerely,