Computing & Information Sciences Kansas State University CIS 530 / 730: Artificial Intelligence Lecture 09 of 42 Wednesday, 17 September 2008 William H. Hsu Department of Computing and Information Sciences, KSU KSOL course page: http://snipurl.com/v9v3 Course web site: http://www.kddresearch.org/Courses/Fall-2008/CIS730 Instructor home page: http:// www.cis.ksu.edu/~bhsu Reading for Next Class: Section 7.5 – 7.7, p. 211 - 232, Russell & Norvig 2 nd edition Logical Agents and Propositional Logic Discussion: Logic in AI
26
Embed
Computing Information Sciences Kansas State University CIS 530 / 730: Artificial Intelligence Lecture 09 of 42 Wednesday, 17 September 2008 William H.
Computing & Information Sciences Kansas State University Type of Training Experience Direct or indirect? Teacher or not? Knowledge about the game (e.g., openings/endgames)? Problem: Is Training Experience Representative (of Performance Goal)? Software Design Assumptions of the learning system: legal move generator exists Software requirements: generator, evaluator(s), parametric target function Choosing a Target Function ChooseMove: Board Move (action selection function, or policy) V: Board R (board evaluation function) Ideal target V; approximated target Goal: operational description (approximation) of V Example: Learning to Play Checkers
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Computing & Information SciencesKansas State UniversityCIS 530 / 730: Artificial Intelligence
Lecture 09 of 42
Wednesday, 17 September 2008
William H. HsuDepartment of Computing and Information Sciences, KSU
KSOL course page: http://snipurl.com/v9v3Course web site: http://www.kddresearch.org/Courses/Fall-2008/CIS730
Instructor home page: http://www.cis.ksu.edu/~bhsu
Reading for Next Class:Section 7.5 – 7.7, p. 211 - 232, Russell & Norvig 2nd edition
Logical Agents and Propositional LogicDiscussion: Logic in AI
Computing & Information SciencesKansas State UniversityCIS 530 / 730: Artificial Intelligence
Lecture Outline Reading for Next Class: Sections 7.5 – 7.7, R&N 2e
Today: Logical Agents Classical knowledge representation Limitations of the classical symbolic approach Modern approach: representation, reasoning, learning “New” aspects: uncertainty, abstraction, classification paradigm
Next Week: Start of Material on Logic Representation: “a bridge between learning and reasoning” (Koller) Basis for automated reasoning: theorem proving, other inference
Computing & Information SciencesKansas State University
Type of Training Experience Direct or indirect? Teacher or not? Knowledge about the game (e.g., openings/endgames)?
Problem: Is Training Experience Representative (of Performance Goal)? Software Design
Assumptions of the learning system: legal move generator exists Software requirements: generator, evaluator(s), parametric target
function Choosing a Target Function
ChooseMove: Board Move (action selection function, or policy) V: Board R (board evaluation function) Ideal target V; approximated target Goal: operational description (approximation) of V
V̂
Example:Learning to Play Checkers
Computing & Information SciencesKansas State University
A Target Function forLearning to Play Checkers
Possible Definition
If b is a final board state that is won, then V(b) = 100 If b is a final board state that is lost, then V(b) = -100 If b is a final board state that is drawn, then V(b) = 0 If b is not a final board state in the game, then V(b) = V(b’) where b’ is the
best final board state that can be achieved starting from b and playing optimally until the end of the game
Correct values, but not operational Choosing a Representation for the Target Function
Collection of rules? Neural network? Polynomial function (e.g., linear, quadratic combination) of board features? Other?
A Representation for Learned Function
bp/rp = number of black/red pieces; bk/rk = number of black/red kings;
bt/rt = number of black/red pieces threatened (can be taken next turn)
bwbwbwbwbwbww bV 6543210 rtbtrkbkrpbp ˆ
Computing & Information SciencesKansas State University
Training Procedure for Learning to Play Checkers
Obtaining Training Examples the target function the learned function the training value
One Rule For Estimating Training Values:
Choose Weight Tuning Rule Least Mean Square (LMS) weight update rule: REPEAT
Select a training example b at randomCompute the error(b) for this training exampleFor each board feature fi, update weight wi as follows:
where c is a small, constant factor to adjust the learning rate
bV̂ bV
bVtrain
bVbV Successortrainˆ
bVbV berror ˆ train
berrorfcww iii
Computing & Information SciencesKansas State University
Design Choices forLearning to Play Checkers
Completed Design
Determine Type ofTraining Experience
Gamesagainst experts
Gamesagainst self
Table ofcorrect moves
DetermineTarget Function
Board valueBoard move
Determine Representation ofLearned Function
Polynomial Linear functionof six features
Artificial neuralnetwork
DetermineLearning Algorithm
Gradientdescent
Linearprogramming
Computing & Information SciencesKansas State University
Knowledge Bases
Adapted from slides by S. RussellUC Berkeley
Computing & Information SciencesKansas State University
Simple Knowledge-Based Agent
Figure 6.1 p. 152 R&NAdapted from slides by S. RussellUC Berkeley
Computing & Information SciencesKansas State UniversityFriday, 14 Sep 2007CIS 530 / 730: Artificial Intelligence
Overview Today’s Reading
Sections 7.1 – 7.4, Russell and Norvig 2e Recommended references: Nilsson and Genesereth (Logical Foundations of
AI) Previously: Logical Agents
Knowledge Bases (KB) and KB agents Motivating example: Wumpus World Logic in general Syntax of propositional calculus
Today Propositional calculus (concluded) Normal forms Production systems Predicate logic Introduction to First-Order Logic (FOL): examples, inference rules (sketch)
Next Week: First-Order Logic Review, Resolution
Computing & Information SciencesKansas State UniversityFriday, 14 Sep 2007CIS 530 / 730: Artificial Intelligence