The paper argues for modeling ethics in RL as relatively stable habits and dispositions rather than rules or scalar rewards, and provides a four-part roadmap using social learning, multi-objective methods, regularization, and diverse ethical traditions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Toward Virtuous Reinforcement Learning: A Critique and Roadmap
The paper argues for modeling ethics in RL as relatively stable habits and dispositions rather than rules or scalar rewards, and provides a four-part roadmap using social learning, multi-objective methods, regularization, and diverse ethical traditions.