no code implementations • 10 Nov 2023 • Shi Gu, Marcelo G Mattar, Huajin Tang, Gang Pan
While advances in artificial intelligence and neuroscience have enabled the emergence of neural networks capable of learning a wide variety of tasks, our understanding of the temporal dynamics of these networks remains limited.
no code implementations • 29 Nov 2021 • Yizhi Yuan, Marcelo G Mattar
This usefulness is quantified as the expected gain from replaying the experience, a quantity often approximated as the prediction error (TD-error).