Paper proves near-minimax rates for quantile distributional RL
A quantile fixed-point estimator matches local asymptotic minimax risk, with resolution-independent rates when reward densities are bounded away from zero.
1 stories, newest first · one card per story
A quantile fixed-point estimator matches local asymptotic minimax risk, with resolution-independent rates when reward densities are bounded away from zero.
Today 1.6K readers · 2.4K views · 774 reads · all time 189K views