Introduces priced face-crossing via normal-fan geometry on occupancy polytopes to decompose dynamic regret into intrinsic motion cost plus within-face error in non-stationary adversarial MDPs.
Gilles Blanchard, Aniket Anand Deshmukh, Urun Doğan, Gyemin Lee, and Clayton Scott
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
other 1polarities
unclear 1representative citing papers
The paper defines an intrinsic drift budget C_T in Fisher-Rao distance along the learner-environment trajectory and proves prequential reproducibility gaps bounded by order T^{-1/2} + C_T/T with a matching lower bound on regular subclasses.
ForgeVLA enables federated VLA model training from unlabeled vision-action pairs by recovering language via embodied classifiers and using contrastive planning plus adaptive aggregation to avoid feature collapse.
RASP-Tuner matches or beats GP-UCB and CMA-ES regret on seven of nine synthetic non-stationary tasks while running 8-12 times faster per step.
citing papers explorer
-
Priced Motion Through Optimal Faces: A Normal-Fan Geometry for Non-Stationary Adversarial MDPs
Introduces priced face-crossing via normal-fan geometry on occupancy polytopes to decompose dynamic regret into intrinsic motion cost plus within-face error in non-stationary adversarial MDPs.
-
Learning under Distributional Drift: Prequential Reproducibility as an Intrinsic Statistical Resource
The paper defines an intrinsic drift budget C_T in Fisher-Rao distance along the learner-environment trajectory and proves prequential reproducibility gaps bounded by order T^{-1/2} + C_T/T with a matching lower bound on regular subclasses.
-
ForgeVLA: Federated Vision-Language-Action Learning without Language Annotations
ForgeVLA enables federated VLA model training from unlabeled vision-action pairs by recovering language via embodied classifiers and using contrastive planning plus adaptive aggregation to avoid feature collapse.
-
RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments
RASP-Tuner matches or beats GP-UCB and CMA-ES regret on seven of nine synthetic non-stationary tasks while running 8-12 times faster per step.