Reward Function Categories

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

• Reward Functionconcept0.878
  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.
• Seven Reward Function Groupsconcept0.822
  The seven categories (Objective only, Expect only, Compare only, and four combinations) structuring the experiment
• Optimal Reward Frameworkframework0.764
  Framework from Singh, Lewis, and Barto 2009 used to select best-performing reward functions via grid search
• How can reward functions be meaningfully specified when the same outcome may be valuable or detrimental depending on context?question0.737
  Motivates active inference's solution: learning prior preferences from interaction rather than external specification.
• Happiness Function f[h]method0.733
  Subjective reward signal from Dubey et al. 2022 balancing objective reward, expectations, and comparisons; extended in this paper
• Reward improvementconcept0.729
  The increase in reward during training, whose dynamics align with those of causal emergence in successful agents.
• Reward Hypothesisconcept0.710
  The claim in RL that any goal can be expressed as maximizing the expected cumulative sum of a scalar reward signal.
• Reward Seekingconcept0.701
  Pragmatic or extrinsic value component of expected free energy; preference maximization.