Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281698803> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4281698803 abstract "Machine-learned black-box policies are ubiquitous for nonlinear control problems. Meanwhile, crude model information is often available for these problems from, e.g., linear approximations of nonlinear dynamics. We study the problem of equipping a black-box control policy with model-based advice for nonlinear control on a single trajectory. We first show a general negative result that a naive convex combination of a black-box policy and a linear model-based policy can lead to instability, even if the two policies are both stabilizing. We then propose an adaptive $lambda$-confident policy, with a coefficient $lambda$ indicating the confidence in a black-box policy, and prove its stability. With bounded nonlinearity, in addition, we show that the adaptive $lambda$-confident policy achieves a bounded competitive ratio when a black-box policy is near-optimal. Finally, we propose an online learning approach to implement the adaptive $lambda$-confident policy and verify its efficacy in case studies about the CartPole problem and a real-world electric vehicle (EV) charging problem with data bias due to COVID-19." @default.
- W4281698803 created "2022-06-13" @default.
- W4281698803 creator A5005758616 @default.
- W4281698803 creator A5006928264 @default.
- W4281698803 creator A5062565732 @default.
- W4281698803 creator A5069455858 @default.
- W4281698803 creator A5070396630 @default.
- W4281698803 creator A5071284374 @default.
- W4281698803 date "2022-06-02" @default.
- W4281698803 modified "2023-09-27" @default.
- W4281698803 title "Equipping Black-Box Policies with Model-Based Advice for Stable Nonlinear Control" @default.
- W4281698803 doi "https://doi.org/10.48550/arxiv.2206.01341" @default.
- W4281698803 hasPublicationYear "2022" @default.
- W4281698803 type Work @default.
- W4281698803 citedByCount "0" @default.
- W4281698803 crossrefType "posted-content" @default.
- W4281698803 hasAuthorship W4281698803A5005758616 @default.
- W4281698803 hasAuthorship W4281698803A5006928264 @default.
- W4281698803 hasAuthorship W4281698803A5062565732 @default.
- W4281698803 hasAuthorship W4281698803A5069455858 @default.
- W4281698803 hasAuthorship W4281698803A5070396630 @default.
- W4281698803 hasAuthorship W4281698803A5071284374 @default.
- W4281698803 hasBestOaLocation W42816988031 @default.
- W4281698803 hasConcept C112680207 @default.
- W4281698803 hasConcept C112972136 @default.
- W4281698803 hasConcept C119857082 @default.
- W4281698803 hasConcept C120665830 @default.
- W4281698803 hasConcept C121332964 @default.
- W4281698803 hasConcept C126255220 @default.
- W4281698803 hasConcept C1276947 @default.
- W4281698803 hasConcept C134306372 @default.
- W4281698803 hasConcept C13662910 @default.
- W4281698803 hasConcept C154945302 @default.
- W4281698803 hasConcept C158622935 @default.
- W4281698803 hasConcept C199360897 @default.
- W4281698803 hasConcept C2524010 @default.
- W4281698803 hasConcept C2775924081 @default.
- W4281698803 hasConcept C2778113609 @default.
- W4281698803 hasConcept C2779955035 @default.
- W4281698803 hasConcept C33923547 @default.
- W4281698803 hasConcept C34388435 @default.
- W4281698803 hasConcept C41008148 @default.
- W4281698803 hasConcept C47446073 @default.
- W4281698803 hasConcept C62520636 @default.
- W4281698803 hasConcept C94966114 @default.
- W4281698803 hasConceptScore W4281698803C112680207 @default.
- W4281698803 hasConceptScore W4281698803C112972136 @default.
- W4281698803 hasConceptScore W4281698803C119857082 @default.
- W4281698803 hasConceptScore W4281698803C120665830 @default.
- W4281698803 hasConceptScore W4281698803C121332964 @default.
- W4281698803 hasConceptScore W4281698803C126255220 @default.
- W4281698803 hasConceptScore W4281698803C1276947 @default.
- W4281698803 hasConceptScore W4281698803C134306372 @default.
- W4281698803 hasConceptScore W4281698803C13662910 @default.
- W4281698803 hasConceptScore W4281698803C154945302 @default.
- W4281698803 hasConceptScore W4281698803C158622935 @default.
- W4281698803 hasConceptScore W4281698803C199360897 @default.
- W4281698803 hasConceptScore W4281698803C2524010 @default.
- W4281698803 hasConceptScore W4281698803C2775924081 @default.
- W4281698803 hasConceptScore W4281698803C2778113609 @default.
- W4281698803 hasConceptScore W4281698803C2779955035 @default.
- W4281698803 hasConceptScore W4281698803C33923547 @default.
- W4281698803 hasConceptScore W4281698803C34388435 @default.
- W4281698803 hasConceptScore W4281698803C41008148 @default.
- W4281698803 hasConceptScore W4281698803C47446073 @default.
- W4281698803 hasConceptScore W4281698803C62520636 @default.
- W4281698803 hasConceptScore W4281698803C94966114 @default.
- W4281698803 hasLocation W42816988031 @default.
- W4281698803 hasLocation W42816988032 @default.
- W4281698803 hasOpenAccess W4281698803 @default.
- W4281698803 hasPrimaryLocation W42816988031 @default.
- W4281698803 hasRelatedWork W1532893707 @default.
- W4281698803 hasRelatedWork W2002316083 @default.
- W4281698803 hasRelatedWork W2115030441 @default.
- W4281698803 hasRelatedWork W2121919740 @default.
- W4281698803 hasRelatedWork W2147578878 @default.
- W4281698803 hasRelatedWork W2159990075 @default.
- W4281698803 hasRelatedWork W2507513082 @default.
- W4281698803 hasRelatedWork W2989775562 @default.
- W4281698803 hasRelatedWork W3033909816 @default.
- W4281698803 hasRelatedWork W4384695901 @default.
- W4281698803 isParatext "false" @default.
- W4281698803 isRetracted "false" @default.
- W4281698803 workType "article" @default.