Differential privacy in policy optimization adds sample complexity costs that often appear as lower-order terms rather than dominating the bounds.
An improved analysis of (variance- reduced) policy gradient and natural policy gradient methods.Advances in Neural Information Processing Systems, 33:7624–7636
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
The k-step policy gradient converges exponentially close to the optimal deterministic policy in restricted classes, achieving O(1/T) rates under smoothness assumptions without distribution mismatch factors.
citing papers explorer
-
On the Sample Complexity of Differentially Private Policy Optimization
Differential privacy in policy optimization adds sample complexity costs that often appear as lower-order terms rather than dominating the bounds.
-
Revisiting Policy Gradients for Restricted Policy Classes: Escaping Myopic Local Optima with $k$-step Policy Gradients
The k-step policy gradient converges exponentially close to the optimal deterministic policy in restricted classes, achieving O(1/T) rates under smoothness assumptions without distribution mismatch factors.