concept
active
concept:ae-1-agency-learning-from-feedback-and-flexible-responsiveness-to-competing-goalsAE-1: Agency: Learning from feedback and flexible responsiveness to competing goals
Indicator of agency requiring goal pursuit and flexibility.
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (3)
concept
- Reinforcement learning (RL)associated_withMachine learning paradigm where agents learn to maximize cumulative reward through interaction.
- Agencyassociated_withCapacity for autonomous action; requires formal definition linking to selfhood, control, and sense of agency.
- Indicator: consumer system that relies on 'real' tagged perceptions for rational action.
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 controlconcept0.786Indicator of embodiment requiring forward models used for perception or motor control.
- DeepMind's Transformer-based adaptive agent trained with meta-RL in a 3D virtual environment.
- 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.
- Proposed formalization of the spectrum from mechanical to cognitive control via energy-efficiency of intervention
- The subjective feeling of controlling one's actions.