Causal emergence in RL agents' internal representations predicts final reward and tracks learning progress across diverse tasks and algorithms.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Causally Emergent Alignment Hypothesis: Causal Emergence Aligns with and Predicts Final Reward in Reinforcement Learning Agents
Causal emergence in RL agents' internal representations predicts final reward and tracks learning progress across diverse tasks and algorithms.