The work establishes the first DP regret bound of order O(K^{3/5}) for model-free online RL under general function approximation and the first coverability-based regret bound for batched non-private RL.
arXiv preprint arXiv:2202.05567 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
Differential privacy in policy optimization adds sample complexity costs that often appear as lower-order terms rather than dominating the bounds.
Replaces determinant growth with generalized Rayleigh quotient for rare switching in private linear bandits to control worst-direction volume despite non-monotonic design matrices from noise.
citing papers explorer
-
Towards Differentially Private Reinforcement Learning with General Function Approximation
The work establishes the first DP regret bound of order O(K^{3/5}) for model-free online RL under general function approximation and the first coverability-based regret bound for batched non-private RL.
-
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.
-
When Determinants Are Not Enough: Private Rare Switching
Replaces determinant growth with generalized Rayleigh quotient for rare switching in private linear bandits to control worst-direction volume despite non-monotonic design matrices from noise.