The paper proposes an Adaptive Safety Architecture with a mutual-information-based Compound Uncertainty Coefficient, MaxInfoRL policies, and adaptive constraints to actively resolve compound epistemic uncertainty in RL rather than passively enduring it.
arXiv preprint (2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Breaking the Epistemic Trap: Active Perception Under Compound Uncertainty
The paper proposes an Adaptive Safety Architecture with a mutual-information-based Compound Uncertainty Coefficient, MaxInfoRL policies, and adaptive constraints to actively resolve compound epistemic uncertainty in RL rather than passively enduring it.