Processing math: 100%

Eligible Traces

Beside n-step TD methods, there is another mechanism called eligible traces that unify TD and Monte Carlo. Setting λ in TD(λ) from 0 to 1, we end up with a spectrum ranging from TD methods, when λ=0 to Monte Carlo methods with λ=1. ...

March 13, 2022 · 25 min · Trung H. Nguyen