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.
Differentially private empirical risk minimization
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Proposes OPAC for trajectory-level offline RL achieving 𝓣O(H^{2}√(C_sa(π*)/n)) bounds with matching lower bound, plus conditions for tractability in generalized nonlinear outcome settings.
The paper defines a Gradient Gap for RLVR policy gradients and proves a sharp step-size threshold below which training converges and above which it collapses, with predictions for length and success-rate scaling validated in simulations and on Qwen2.5-Math-7B.
citing papers explorer
-
When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?
Proposes OPAC for trajectory-level offline RL achieving 𝓣O(H^{2}√(C_sa(π*)/n)) bounds with matching lower bound, plus conditions for tractability in generalized nonlinear outcome settings.