StaQ, a finite-memory Policy Mirror Descent algorithm, converges to the optimal entropy-regularized policy with a sufficiently large window of past Q-functions and performs competitively with baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
StaQ it! Growing neural networks for Policy Mirror Descent
StaQ, a finite-memory Policy Mirror Descent algorithm, converges to the optimal entropy-regularized policy with a sufficiently large window of past Q-functions and performs competitively with baselines.