Skip to main content
Back to course
Log in
Get started
Someone wanted to learn this too, so Grasp built them a personal learning path.
Create your own
Physical AI
·
Module 1
Embodiment and Sensorimotor Intelligence
1
Embodied Agents and the Perception–Action Loop
Distinguish an embodied agent from a passive prediction system using the perception-action loop.
Distinguish an embodied agent from a passive prediction system using the perception-action loop.
2
Formulating Embodied Tasks as Partially Observable Markov Decision Processes
Formulate an embodied task as a partially observable Markov decision process.
Formulate an embodied task as a partially observable Markov decision process.
3
How Morphology Shapes Perception, Action, and Learning
Analyze how morphology constrains an agent’s observations, actions, and learnable behaviors.
Analyze how morphology constrains an agent’s observations, actions, and learnable behaviors.
4
Defining Observation and Action Spaces for Embodied Tasks
Specify observation and action spaces for a simulated embodied task.
Specify observation and action spaces for a simulated embodied task.
5
Designing Effective Reward, Success, and Termination Criteria
Define reward, success, and termination criteria without introducing unintended incentives.
Define reward, success, and termination criteria without introducing unintended incentives.
6
When Embodied Policies Need Memory
Determine when an embodied policy requires memory because the current observation is insufficient.
Determine when an embodied policy requires memory because the current observation is insufficient.
Next module isn't ready yet,
Back to course
Previous module
Next module