CS 4408 Artificial Intelligence - Discussion post 2.19

pdf

School

University of the People *

*We aren’t endorsed by this school

Course

4408

Subject

Computer Science

Date

Nov 24, 2024

Type

pdf

Pages

4

Uploaded by SargentStar10254

Report
CS 4408 Artificial Intelligence Discussion Forum Unit 2 Date: 29/06/2023
Re: Discussion Forum Unit 1 by XXXX XXxxx XXXXXX Tuesday, 27 June 2023, 1:46 PM AI agents can be categorized by their Performance (how are the goals of the agent measured?), Environment (what physical or virtual surroundings does the agent encounter?), Actuators (what physical or virtual parts does the agent use to create output?), and Sensors (how does the agent receive input?). These four categories can be abbreviated as PEAS. There can also be several types of environment types (Introduction, n.d.): -Fully Observable and Partially Observable (does the agent have total knowledge of the whole environment, or is some hidden or not accessible?); - Deterministic and Stochastic (does the agent and the environment’s current state determine the next state, or is the next state random and unpredictable?); - Static and Dynamic (does the agent’s environment change or stay the same while the agent makes decisions?); -Discrete and Continuous (does the environment have a limited number of possibilities or are the data sources continuously changing?); and -Single Agent and Multi-agent (is the agent acting alone or with other agents?). Given these definitions, let’s look at some example agents and consider their possible PEAS and environment types. Self-vacuum cleaner P- level of cleanliness for spots cleaned, thoroughness of floor coverage, lack of damage to environment, speed (done in a reasonable amount of time), regularity of vacuum timing, ability to return to charger before losing power, sufficient battery life E- different floor types, charging home, furniture, people, pets, walls, stairs A- wheels, vacuum brushes/rollers, cushioned edges, dirt collectors S- dirt sensors, wall sensors, cliff (stair) sensors, object sensors (Layton, n.d.) Environment types: partially observable (i t doesn’t have all the information at once), deterministic (where it has already cleaned and finds out about the environment is used in the algorithm to determine where to clean next), dynamic in that people, pets and furniture can move during cleaning, discrete because the room size and possibilities for where to clean are limited, single agent. Speech recognition device P- accuracy, speed, variety of languages possible E- person/voice A- text display or printing capability
S- audio sensor for receiving voice input Environment types: fully observable, stochastic, static, discrete (each language has a finite, if large, set of words), single agent Drone searching for a missing person P- area coverage, speed, battery power, height and distance capabilities, success rate, connectivity with other networked drones, ability to return to dock before losing power E- geographical features (such as bodies of water, mountains, etc), manmade structures (such as buildings, power lines and poles, and walls), vegetation (trees, bushes, grass), people, animals, weather A- rotor blades, communication capabilities (bluetooth, wi-fi, radio) S- cameras, infrared sensors, GPS, radar Environment types: partially observable, stochastic, dynamic, continuous, could be multi-agent if connected with other drones for the search but could also be single agent Computer playing chess P- success rate, decision making time E- virtual board, virtual pieces (opponent’s and own), computer hardwar e A- computer software (this was a difficult one for me-- I’m not sure what the computer uses to “move the pieces” ) S- again, I’m not sure other than the computer softwar e Environment types: fully observable, deterministic, static, discrete, single agent Alexa/Siri performing as a smart personal assistant P- answer accuracy, response time, wake word success rate, success rate for various tasks (calendar, lists, calls, texts, etc) E- internet, people, lights, phones/devices A- speaker, lights, video or picture display, text display S- audio receptors Considering each of these agents was an interesting task! I’m looking forward to learning more from my classmates’ posts . References: Introduction. (n.d.) Learning Guide Unit 2: Introduction. University of the People. https://my.uopeople.edu/mod/book/view.php?id=371154&chapterid=44205 8
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
Layton, J. (n.d.) How Robotic Vacuums Work. howstuffworks. https://www.sci.brooklyn.cuny.edu/~sklar/teaching/f06/cis1.0/ papers/roomba-howstuffworks.pdf 594 words In reply to XXXX XXXXX XXXXX Re: Discussion Forum Unit 1 by Xxxxx Xxxxxxx Thursday, 29 June 2023, 12:59 AM Hi Xxxx, Thanks for your encouraging words and thorough response to my post! And you made a good point about the speech recognition device possibly having a dynamic environment, I hadn't thought of that. 34 words