concept
active
concept:adaptive-agent-adaAdaptive Agent (AdA)
DeepMind's Transformer-based adaptive agent trained with meta-RL in a 3D virtual environment.
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Organism's belief-guided action selection that instantiates generative model and maintains phenotypic states
- Any autonomous system including living and non-living forms that embodies a perception-action cycle and tries to navigate and persist in an environment
- Indicator of agency requiring goal pursuit and flexibility.
- Synthetic agents (here RL-trained neural networks) whose causal emergence was previously largely unknown; the paper addresses this gap.
- Property exhibited by the economy as a complex system, supporting its classification as a collective intelligence.
- Higher-level individuals (e.g., embryo, swarm) that arise from cooperative subunits, possessing goals not assignable to any one component.
- Capacity for autonomous action; requires formal definition linking to selfhood, control, and sense of agency.
- The varied neural network architectures used in the RL experiments to test whether the alignment phenomenon generalizes across architectures.