The paper establishes a correspondence between Signal Temporal Logic and stratification theory, allowing STL formulas to be viewed as stratifications of space-time and applied to analyze DRL embedding spaces via robustness rewards.
Less is more: Local intrinsic dimensions of contextual language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Stratifying Reinforcement Learning with Signal Temporal Logic
The paper establishes a correspondence between Signal Temporal Logic and stratification theory, allowing STL formulas to be viewed as stratifications of space-time and applied to analyze DRL embedding spaces via robustness rewards.