1. Designed by Gusz Eiben & Mark Hoogendoorn
On-line adaptation, learning,
evolution
2. Designed by Gusz Eiben & Mark Hoogendoorn
Outline
âą Population-based Adaptive Systems
âą Types of adaptation: evolution, individual
(lifetime) learning, social learning
âą Machine learning
âą Reinforcement learning
âą Off-line vs. on-line adaptation
3. Designed by Gusz Eiben & Mark Hoogendoorn
Population-based Adaptive Systems
PAS have two essential features
âąThey consist of a group of basic units that can
perform actions, e.g., computation,
communication, interaction, etc.
âąThe ability to adapt at
â individual level (modify agent ) and/or
â group level (add/remove agent).
4. Designed by Gusz Eiben & Mark Hoogendoorn
Types of adaptation
âą Evolutionary learning (EL): Changes at population
level (assumed non-Lamarckian)
âą Lifetime learning (LL): Changes at agent level
â Individual learning (IL): adaptation autonomously
through a purely internal procedure
â Social learning (SL): adaptation through interaction
/communication
5. Designed by Gusz Eiben & Mark Hoogendoorn
Taxonomy of adaptation
Adaptation
Evolutionary
Learning
Lifetime
Learning
Individual
Learning
Social
Learning
6. Designed by Gusz Eiben & Mark Hoogendoorn
Taxonomy of adaptation 2
Adaptation
Evolutionary
Learning
Lifetime
Learning
Individual
Learning
Social
Learning
Learning
Evolution
7. Designed by Gusz Eiben & Mark Hoogendoorn
Adaptation â operation
âą Operation: controller is being used
â Sensory inputs ï outputs (motor, comm. device)
â Robot behavior changes, not the controller
âą Adaptation: controller is being changed
â Present controller ï new controller
â Uses utility/reward/fitness info
â It may require
âą One single robot â learning
âą More robots â evolution, social learning
âą Adaptation + operation = generate + test
âą Off-line (initial controller design, before start) vs. on-line (after
start)
8. Designed by Gusz Eiben & Mark Hoogendoorn
Genotype
Developmental
Engine(decoder)
Genetic operators:
mutation & xover
Learning
operators
Robot
behavior
State of the
environment
Phenotype =
controller
Reward
Fitness
Selection
operators
9. Designed by Gusz Eiben & Mark Hoogendoorn
Genotype
Developmental
Engine(decoder)
Genetic operators:
mutation & xover
Learning
operators
Robot
behavior
State of the
environment
Phenotype =
controller
Reward
Fitness
Selection
operators
10. Designed by Gusz Eiben & Mark Hoogendoorn
Genotype
Developmental
Engine(decoder)
Genetic operators:
mutation & xover
Learning
operators
Robot
behavior
State of the
environment
Reward
Fitness
Selection
operators
Phenotype
controllershape
11. Designed by Gusz Eiben & Mark Hoogendoorn
Phenotype
Genotype
Developmental
Engine(decoder)
Genetic operators:
mutation & xover
Learning
operators
Robot
behavior
State of the
environment
Reward
Fitness
Selection
operators
controllershape
12. Designed by Gusz Eiben & Mark Hoogendoorn
Evolutionary loop
Genotype
DevelopmentalEngine
Genetic operators:
mutation & xover
Learning operator(s)
Robot
behavior
Changes in
environment
Controller =
phenotype
Reward
Fitness
Selection
operator(s)
13. Designed by Gusz Eiben & Mark Hoogendoorn
Learning loop
Genotype
DevelopmentalEngine
Genetic operators:
mutation & xover
Learning operator(s)
Robot
behavior
Changes in
environment
Controller =
phenotype
Reward
Fitness
Selection
operator(s)
14. Designed by Gusz Eiben & Mark Hoogendoorn
ENVIRONMENTAGENT
Reward r(t)
State s(t)
Action a(t)
15. Designed by Gusz Eiben & Mark Hoogendoorn
Reinforcement learning
Agent in situation/state st chooses action at
World changes to situation/state st+1
Agent perceives situation st+1 and gets reward rt+1
Telling the agent what to do is its
POLICY Ït(s, a) = P r{at = a|st = s}
Given the situation at time t is s, the policy gives the probability the agentâs
action will be a.
For example: Ït(s, goforward) = 0.5, Ït(s, gobackward) = 0.5.
Reinforcement learning â Get/ïŹnd/learn the policy
16. Designed by Gusz Eiben & Mark Hoogendoorn
Further reading
âą Evert Haasdijk and A.E. Eiben and Alan F.T.
Winfield, Individual Social and Evolutionary
Adaptation in Collective Systems , Serge
Kernbach (eds.) , Handbook of Collective
Robotics , Pan Stanford , 2011