CGPA enables certified speculative execution of untrusted AI proposals in constrained sequential decisions via verifier rejection, conformal boundary gating, and solver deferral, yielding zero violations and regret within noise of the oracle.
Safe reinforcement learning via probabilistic shields
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
The thesis presents Pino, an end-to-end pipeline that supervises reinforcement learning agents with argumentation-based normative advisors, introduces an algorithm for automatic argument extraction, and defines a mitigation strategy for norm avoidance.
citing papers explorer
-
What if Pinocchio Were a Reinforcement Learning Agent: A Normative End-to-End Pipeline
The thesis presents Pino, an end-to-end pipeline that supervises reinforcement learning agents with argumentation-based normative advisors, introduces an algorithm for automatic argument extraction, and defines a mitigation strategy for norm avoidance.