liveBook · Manning

Policy

As explained in Robotics for Programmers

A policy is a mapping from observations or states to actions that specifies an agent's behavior.

A policy maps a robot’s observations or environmental states to actions, specifying how an agent behaves. section 5.2

In reinforcement learning, an agent interacts with an environment, receives rewards, and learns a policy that captures behavior associated with high rewards. section 5.2

Simulation-to-real control

Train a policy in simulation, then use it to control a real robot in target scenarios; adapt it with real-robot training when necessary. section 5.2

How Robotics for Programmers covers it

How deep it goes
Defines the observation-to-action mapping and connects it to reward maximization and simulation-to-real transfer.
Examples
Uses an agent interacting with an environment and a policy trained in simulation before real-robot deployment.
What you can do after
Operate a robot in target scenarios by applying a learned policy to its observations or states.
How it connects
Connects policy with reinforcement learning, rewards, simulation, machine learning, and robot control.

Also explained in

Compare how 21 books explain policy →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Robotics for Programmers. The section links point to the parts of the book it draws on.