QED bounds cross-run KL divergence in Boltzmann policies by setting temperature proportional to Q-disagreement and reduces return variance by two orders of magnitude on 18 continuous-control tasks without performance loss.
and Barto, Andrew G
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
other 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Behavior-Consistent Deep Reinforcement Learning
QED bounds cross-run KL divergence in Boltzmann policies by setting temperature proportional to Q-disagreement and reduces return variance by two orders of magnitude on 18 continuous-control tasks without performance loss.