Reward Hacking

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

• Reward Seekingconcept0.752
  Pragmatic or extrinsic value component of expected free energy; preference maximization.
• ubiquitous hacking in biologyconcept0.751
  Biological parts exploit each other, lacking commitment to original interpretations.
• Reward improvementconcept0.746
  The increase in reward during training, whose dynamics align with those of causal emergence in successful agents.
• Reward Functionconcept0.740
  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.
• Morphogenetic Hackingmethod0.739
• Final rewardconcept0.718
  The total reward accumulated by an RL agent at the end of training, used as the primary performance metric predicted by early causal emergence.
• Reward Hypothesisconcept0.706
  The claim in RL that any goal can be expressed as maximizing the expected cumulative sum of a scalar reward signal.
• Optimal Reward Frameworkframework0.705
  Framework from Singh, Lewis, and Barto 2009 used to select best-performing reward functions via grid search