Causal emergence provides new perspectives for causal representation learning, interpreting latent variables as emergent causalities.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Causal emergence identification tasks can be understood as causal representation learning tasks.claim0.873
  Authors propose a conceptual mapping between CE identification and CRL.
• Causal emergence alignment with learning is a shared axis comparing biological and artificial creatures.claim0.848
  Assertion that the correlation between causal emergence and learning constitutes another way biological and artificial intelligences converge.
• Causal emergence is defined by the difference in the EI values between the macro-level and micro-level.quote0.848
  Core definition from §1.
• Representational dynamics of causal emergence align with reward improvement in most tasks.finding0.839
  The trajectory of causal emergence through training mirrors the reward improvement curve across the majority of tested environments.
• Causal emergence may be a previously undisclosed axis of reorganization of neural representations in RL agents.claim0.838
  Authors' interpretive assertion that the observed alignment reveals a novel organizing principle of neural representation dynamics.
• Causal emergence is widespread across measures of causation, not just EI.claim0.835
  Claim by Comolatti & Hoel (2022) endorsed by this survey.
• Causal emergence predictive of final reward early in RL training across multiple algorithms, architectures, and environments.finding0.827
  Empirical result: CE measurements correlate with and predict learning performance in RL agents.
• Causal emergence can enable causal interventions to create better RL agents.claim0.820
  Assertion that understanding causal emergence may lead to methods for manipulating agent representations to improve performance.