The authors cast multimodal remote inference as an SMDP to minimize error as a function of the AoI vector, proving an index-based threshold structure for two modalities and developing the EAST policy via multichain policy iteration for more modalities, with low-complexity variants.
From freshness to effectiveness: Goal-oriented sampling for remote decision making,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multimodal Remote Inference
The authors cast multimodal remote inference as an SMDP to minimize error as a function of the AoI vector, proving an index-based threshold structure for two modalities and developing the EAST policy via multichain policy iteration for more modalities, with low-complexity variants.