Dont forget your research paper - PowerPoint PPT Presentation

1 / 19
About This Presentation
Title:

Dont forget your research paper

Description:

AAAI (American Association of Artificial Intelligence) ... Develop a PEAS description of the task environment for a RoboCup participant. ... – PowerPoint PPT presentation

Number of Views:20
Avg rating:3.0/5.0
Slides: 20
Provided by: systema178
Category:

less

Transcript and Presenter's Notes

Title: Dont forget your research paper


1
Dont forget your research paper
  • Find and read a paper from an acceptable AI
    source
  • SIGART (www.acm.org)
  • AAAI (American Association of Artificial
    Intelligence)
  • Posted to a university website and published in a
    conference or journal dealing with AI
  • A paper from one of the AI journals I handed out.
  • Write a 2-4 page (600-1200 word) response

2
Review from last time
  • When describing and designing agents we need to
    consider the task environment
  • Performance Measure
  • Environment
  • Actuators
  • Sensors

3
Review from last time
  • We often describe the environment based on six
    attributes.
  • Fully/partially observable
  • Deterministic/stochastic
  • Episodic/sequential
  • Static/dynamic
  • Discrete/continuous
  • Single agent/multiagent

4
Environment Types
5
Environment Types
6
Environment Types
7
Environment Types
8
Environment Types
9
Environment Types
10
Environment Types
11
Environment Types
  • The environment type largely determines the agent
    design
  • The real world is (of course) partially
    observable, stochastic, sequential, dynamic,
    continuous, multi-agent

12
RoboCup
  • By the year 2050, develop a team of fully
    autonomous humanoid robots that can win against
    the human world soccer champion team.
    (www.robocup.org).
  • Develop a PEAS description of the task
    environment for a RoboCup participant.
  • Include a thorough classification of the
    environment using RNs six properties of task
    environments.

13
Agent Types
  • Agent architecture program
  • Simple reflex agent
  • Reflex agent with state
  • Goal-based agent
  • Utility-based agent
  • Learning agent (arguably not a 5th agent but a
    different model of any of the previous agents).

14
Agent Types
  • Simple reflex agent

15
Agent Types
  • Reflex agent with state

16
Agent Types
  • Goal-based agent

17
Agent Types
  • Utility-based agent

18
Agent Types
  • Learning agent

19
Prep to move onMissionaries and Cannibals
  • Three missionaries and three cannibals
  • Want to cross a river using one canoe.
  • Canoe can hold up to two people.
  • Can never be more cannibals than missionaries on
    either side of the river.
  • Aim To get all safely across the river without
    any missionaries being eaten.
  • Variant 5 and 5 with a canoe that holds 3
Write a Comment
User Comments (0)
About PowerShow.com