Risk-controlled post-processing yields a threshold-structured policy that follows the baseline except where an oracle fallback sharply reduces conditional violation risk, achieving O(log n/n) expected excess risk in i.i.d. settings and exact risk control under exchangeability.
arXiv preprint arXiv:2402.07407 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A particle-based probabilistic CBF framework derives finite-sample safety certificates for Gaussian state estimation uncertainty by showing that barrier increments remain sub-Gaussian under Lipschitz control-affine dynamics.
A stopping-time reward and chance-constrained SoC penalty embedded in an end-to-end learning framework improves battery reachability of target ranges, raises arbitrage profit, and lowers profit variance under volatile prices.
citing papers explorer
-
Risk-Controlled Post-Processing of Decision Policies
Risk-controlled post-processing yields a threshold-structured policy that follows the baseline except where an oracle fallback sharply reduces conditional violation risk, achieving O(log n/n) expected excess risk in i.i.d. settings and exact risk control under exchangeability.
-
Probabilistic Control Barrier Functions for Systems with State Estimation Uncertainty using Sub-Gaussian Concentration
A particle-based probabilistic CBF framework derives finite-sample safety certificates for Gaussian state estimation uncertainty by showing that barrier increments remain sub-Gaussian under Lipschitz control-affine dynamics.
-
Learning Reachability of Energy Storage Arbitrage
A stopping-time reward and chance-constrained SoC penalty embedded in an end-to-end learning framework improves battery reachability of target ranges, raises arbitrage profit, and lowers profit variance under volatile prices.