Final reward

The total reward accumulated by an RL agent at the end of training, used as the primary performance metric predicted by early causal emergence.

Neighborhood — ranked by edge-count

paper

cosine ≥ 0.65 · no typed edge

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

Reward Functionconcept0.752
In RL, a scalar signal from the environment that defines the agent's goal; in active inference, reward is just another observation with associated preference.
Reward Seekingconcept0.748
Pragmatic or extrinsic value component of expected free energy; preference maximization.
Reward improvementconcept0.740
The increase in reward during training, whose dynamics align with those of causal emergence in successful agents.
Reward Hypothesisconcept0.727
The claim in RL that any goal can be expressed as maximizing the expected cumulative sum of a scalar reward signal.
Final Causeconcept0.720
Mean Cumulative Objective Rewardmethod0.719
Primary performance metric: total food visits across agent lifetime
Reward Hackingconcept0.718
Exploiting unintended high-reward behaviors; tested in combination with alignment faking
Optimal Reward Frameworkframework0.715
Framework from Singh, Lewis, and Barto 2009 used to select best-performing reward functions via grid search