Reward Function

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.

Neighborhood — ranked by edge-count

Concepts (1)

concept

Stress
associated_with
Defined as discrepancy between current and optimal state; key driver of homeostatic action and intelligence across all systems.

Related by similarity (8)

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 Function Categoriesmethod0.878
Seven categories determined by which components of f[h] are activated: Objective only, Expect only, Compare only, and combinations
Functionconcept0.798
The practical, working aspect of a building; reinterpreted as the dynamic harmony of moving centers.
Seven Reward Function Groupsconcept0.788
The seven categories (Objective only, Expect only, Compare only, and four combinations) structuring the experiment
Happiness Function f[h]method0.786
Subjective reward signal from Dubey et al. 2022 balancing objective reward, expectations, and comparisons; extended in this paper
Optimal Reward Frameworkframework0.785
Framework from Singh, Lewis, and Barto 2009 used to select best-performing reward functions via grid search
Reward improvementconcept0.783
The increase in reward during training, whose dynamics align with those of causal emergence in successful agents.
Loss Functionconcept0.778
In machine learning, a function measuring the distance between current and desired output; analogous to stress.
How can reward functions be meaningfully specified when the same outcome may be valuable or detrimental depending on context?question0.773
Motivates active inference's solution: learning prior preferences from interaction rather than external specification.