By the end of this lecture
Four things you can do.
Trace the agent loop
Perceive, model, plan, act, monitor — and name the interface each stage uses.
Compare world models
Latent, symbolic, hybrid: what each one buys, and what each one costs.
Separate the layers
Task planning, motion planning, control — and the feasibility condition that links them.
Diagnose agent failures
Attribute a failure to grounding, model, planning, execution, or specification.