Optimal Reward Framework

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

• Reward Functionconcept0.785
  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 Function Categoriesmethod0.764
  Seven categories determined by which components of f[h] are activated: Objective only, Expect only, Compare only, and combinations
• Reward Hypothesisconcept0.758
  The claim in RL that any goal can be expressed as maximizing the expected cumulative sum of a scalar reward signal.
• Seven Reward Function Groupsconcept0.731
  The seven categories (Objective only, Expect only, Compare only, and four combinations) structuring the experiment
• Reward improvementconcept0.729
  The increase in reward during training, whose dynamics align with those of causal emergence in successful agents.
• Traditional RL frameworks optimize externally defined reward functions lacking representational depth for mental-state reasoningclaim0.728
  Motivation claim positioning this paper against standard RL approaches
• Goal Directed Frameworkframework0.727
• Frameworkconcept0.717
  1984 Ashton-Tate integrated system with frames, FRED language, and overlapping windows; design reference for Playground's approach.