concept
active
concept:ae-1-minimal-agency-learning-from-feedback-and-selecting-outputs-to-pursue-goals-especially-with-flexible-responsiveness-to-competing-goalsAE-1: Minimal agency: Learning from feedback and selecting outputs to pursue goals, especially with flexible responsiveness to competing goals
Agency and embodiment indicator; supported by GWT, PRM, and PP; key feature shared by animals and AI agents
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- Indicator of agency requiring goal pursuit and flexibility.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- AE-2: Embodiment: Modeling output-input contingencies and using the model in perception or controlconcept0.783Indicator of embodiment requiring forward models used for perception or motor control.
- Embodiment indicator; systems meeting AE-2 likely but not guaranteed to also meet AE-1
- Central methodological claim of TAME: optimal position on the persuadability continuum is found through experiments, not philosophical definition.
- Argument that RL meets the agency indicator.
- Certain kinds of information structures actively facilitate their own transformation and remapping, exhibiting minimal agency.hypothesis0.765Speculative hypothesis that memories themselves are agents.
- Proposed formalization of the spectrum from mechanical to cognitive control via energy-efficiency of intervention
- Concise statement of the free-energy principle's unification of action and perception.