Case Injected Genetic Algorithms

1
Case Injected Genetic Algorithms

• Sushil J. Louis
• Genetic Algorithm Systems Lab (gaslab)
• University of Nevada, Reno
• http//www.cs.unr.edu/sushil
• http//gaslab.cs.unr.edu/
• sushil_at_cs.unr.edu

2
Outline

• Motivation
• What is the technique?
• Genetic Algorithm and Case-Based Reasoning
• Is it useful?
• Combinational Logic Design
• Strike Force Asset Allocation
• TSP
• Scheduling
• Conclusions

3
Genetic Algorithm

• Non-Deterministic, Parallel, Search
• Poorly understood problems
• Evaluate, Select, Recombine
• Population search
• Population member encodes candidate solution
• Building blocks combine to make progress
• More resistant to local optima
• Iterative, requiring many evaluations

4
Motivation

• Deployed systems are expected to confront and
  solve many problems over their lifetime
• How can we increase genetic algorithm performance
  with experience?
• Provide GA with a memory

5
Case-Based Reasoning

• When confronted by a new problem, adapt similar
  (already solved) problems solution to solve new
  problem
• CBR ? Associative Memory Adaptation
• CBR Indexing (on problem similarity) and
  adaptation are domain dependent

6
Case Injected Genetic AlgoRithm

• Combine genetic search with case-based reasoning
• Case-base provides memory
• Genetic algorithm provides adaptation
• Genetic algorithm generates cases
• Any member of the GAs population is a case

7
System
8
Related work

• SeedingKoza, Greffensttette, Ramsey, Louis
• Lifelong learning Thrun
• Key Differences
• Store and reuse intermediate solutions
• Solve sequences of similar problems

9
Combinational Logic Design

• An example of configuration design
• Given a function and a target technology to work
  with design an artifact that performs this
  function subject to constraints
• Target technology Logic gates
• Function Parity checking
• Constraints 2-D gate array

10
Encoding
11
Encoding
12
Parity
13
Which cases to inject?

• Problem distance metric (Louis 97)
• Domain dependent
• Solution distance metric
• Genetic algorithm encodings
• Binary hamming distance
• Real euclidean distance
• Permutation longest common substring

14
Problem similarity
15
Lessons

• Storing and Injecting solutions may not improve
  solution quality
• Storing and Injecting partial solutions does lead
  to improved quality

16
OSSP Performance
17
Solution Similarity
18
Periodic Injection Strategies

• Closest to best
• Furthest from worst
• Probabilistic closest to best
• Probabilistic furthest from worst
• Randomly choose a case from case-base
• Create random individual

19
Setup

• 50, 6-bit combinational logic design problems
• Randomly select and flip bits in parity output to
  define logic function
• Compare performance
• Quality of final design solution (correct output)
• Time to this final solution (in generations)

20
Parameters

• Population size 30
• No of generations 30
• CHC (elitist) selection
• Scaling factor 1.05
• Prob. Crossover 0.95
• Prob. Mutation 0.05

• Store best individual every generation
• Inject every 5 generations (25 32)
• Inject 3 cases (10)
• Multiple injection strategies

Averages over 10 runs
21
Problem distribution
22
Performance - Quality
23
Performance - Time
24
Injection Strategies
25
Solution distribution
26
Strike force asset allocation

• Allocate platforms to targets
• Dynamic
• Changing target priority
• Battlefield conditions
• Popup
• Weather

27
Factors in allocation

• Pilot proficiency
• Asset suitability
• Priority
• Risk
• Route
• Other assets (SEAD)
• Weather

28
Maximize mission success

• Binary encoding
• Platform to multiple targets
• Target can have multiple platforms
• Dynamic battle-space
• Strong time constraints

29
Setup

• 50 problems.
• 10 platforms, 40 assets, 10 targets
• Each platform could be allocated to two targets
• Problems varied in risk matrix
• Popsize80, Generations80, Pc1.0, Pm0.05,
  probabilistic closest to best, injection
  period9, injection 10 of popsize

30
Results
31
TSP

• Find the shortest route that visits every city
  exactly once (except for start city)
• Permutation encoding. Ex 35412
• Similarity metric Longest common subsequence
  (Cormen et al, Introduction to Algorithms)
• 50 problems, move city locations

32
TSP performance
33
Scheduling

• Job shop scheduling problems
• Permutation encoding (Fang)
• Similarity metric Longest common subsequence
  (Cormen et al, Introduction to Algorithms)
• 50 problems, change task lengths

34
JSSP Performance (10x10)
35
JSSP Performance (15x15)
36
Summary

• Case Injected Genetic AlgoRithm A hybrid system
  that combines genetic algorithms with a
  case-based memory
• Defined problem-similarity and solution-similarity
  metrics
• Defined performance metrics and showed
  empirically that CIGAR learns to increase
  performance for sequences of similar problems

37
Conclusions

• Case Injected Genetic AlgoRithm is a viable
  system for increasing performance with experience
• Implications for system design
• Increases performance with experience
• Generates cases during problem solving
• Long term navigable store of expertise
• Design analysis by analyzing case-base