DOC PREVIEW
NCSU CSC 411 - Agent Types

This preview shows page 1 out of 3 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 3 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 3 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

CSC 411 1st Edition Lecture 3 Outline of Last Lecture I. Environment Typesa. Fully vs. Partially observableb. Deterministic vs. Stochasticc. Episodic vs. Sequentiald. Static vs. Dynamice. Discrete vs. Continuousf. Single vs. MultiagentOutline of Current Lecture I. Agent Typesa. Simple reflex agentsb. Model-based reflex agentsc. Goal-based reflex agentsd. Utility-based agentse. Learning agentsII. Statesa. Atomicb. Factoredc. StructuredCurrent LectureSimple reflex agents- Simple but very limited intelligence- Infinite loopso Suppose vacuum cleaner does not keep track of location. What do you do on a clean left of A or right on B is infinite loopo Randomize actionModel-based reflex agents- Know how world evolveso Overtaking car gets closer from behind- How agent’s actions affect the worldo Wheel turned clockwise takes you rightThese notes represent a detailed interpretation of the professor’s lecture. GradeBuddy is best used as a supplement to your own notes, not as a substitute.- Model-based agents update their stateGoal-based agents- Knowing state and environment? Enough?o Taxi can go left, right, straight- Have a goal- Uses knowledge about a goal to guide its actionso E.g., search, planningUtility-based agents- Goals are not always enougho Many action sequences get taxi to destinationo Consider other things: how fast, how safe…- A utility function maps a state onto a real number which describes the associated degreeof happinesso Utility measures which states are preferable to other stateso Maps state to real number (utility or “happiness”)Learning agents- Performance element is what was previously the whole agento Input sensoro Output action- Learning elemento Modifies performance elemento Responsible for improving the performance element with experience- Critic: how the agent is doing w/ respect to the performance standardo Input: checkmate?- Problem generatoro Tries to solve the problem differently instead of optimizingo Suggests actions to come up with new and informative experiencesLearning agents (taxi driver)- Performance element: how it currently drives- Taxi driver makes quick left turn across 3 laneso Critics observe shocking language by passenger and other drivers and informs bad actiono Learning element tries to modify performance elements for futureo Problem generator suggests experiment out something called Brakes on differentroad conditions- Critics not always easyo Shocking languageo Fewer tipso Fewer passengersStates- Atomic: no internal structure- Factored: a set of state variables of interest are identified for problem solving; states are distinguished by the values those variables have- Structured: states consist of objects (as in a factored representation) as well as relationships between


View Full Document

NCSU CSC 411 - Agent Types

Download Agent Types
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Agent Types and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Agent Types 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?