The paper introduces representational empowerment, a mutual information objective that rewards agents for having internally diverse and controllable representations, as an alternative to external reward maximization.
Vime: Variational information maximizing exploration
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Agent-centric learning: from external reward maximization to internal knowledge curation
The paper introduces representational empowerment, a mutual information objective that rewards agents for having internally diverse and controllable representations, as an alternative to external reward maximization.