TDL seemed to capture the idea of pain coming from the mere expectation of punishment, which is different from reinforcement, where the pain comes after the punishment.
Thanks, I’ll keep this in mind when reviewing reinforcement learning.
TDL seemed to capture the idea of pain coming from the mere expectation of punishment, which is different from reinforcement, where the pain comes after the punishment.
Thanks, I’ll keep this in mind when reviewing reinforcement learning.