Non-normal transient amplification is an important contributor to closed-loop variance in RL, and input-side suppression can reduce downstream covariance without altering peak gain.
Stochastic variance reduction for policy gradient estimation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Input-Side Variance Suppression under Non-Normal Transient Amplification in Continuous-Control Reinforcement Learning
Non-normal transient amplification is an important contributor to closed-loop variance in RL, and input-side suppression can reduce downstream covariance without altering peak gain.