More capable RL agents exploit reward misspecifications more often, with phase transitions in behavior, and anomaly detectors can identify misaligned policies.
Bradley Knox, Alessandro Allievi, Holger Banzhaf, Felix Schmitt, and Peter Stone
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2022 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models
More capable RL agents exploit reward misspecifications more often, with phase transitions in behavior, and anomaly detectors can identify misaligned policies.