2. What a machine can do
YASKAWA BUSHIDO PROJECT /
industrial robot vs sword master
Deep Blue vs G. Kasparov
1997
Motion Problem resolution
3.
4.
5. Doncieux, S. (to appear) Creativity: A Driver for Research on Robotics in Open Environments, Intellectica
Performance
Context
Robot A
Robot B
?
??
?
??
Known
Unknown Unknown
6. How can a robot face a new
environment ?
1. Robustness
2. Learning
3. Development
9. 2. Learning
continuous actions & states
Evaluation
Genotype
Fitness
Random generation
Selection
Variation
8.3
00110100111
Termination
Initial conditionsEvaluation
Genotype
Phenotype
Behavior
Environment
Fitness
Evolutionary Robotics
Mouret, J.B., Bredeche, N. et Doncieux S. La robotique
évolutionniste Pour la science n°87, Avril-Juin 2015
Doncieux, S., Bredeche, N., Mouret, J.-B., & Eiben, A. E.
(2015). Evolutionary Robotics: What, Why, and Where to.
Frontiers in Evolutionary Robotics, doi: 10.3389/frobt.
2015.00004
10. A
Kober, J., Bagnell, J. a., & Peters, J. (2013). Reinforcement learning in robotics: A survey.
The International Journal of Robotics Research, 32(11), 1238–1274. doi:10.1177/0278364913495721
2. Learning
The representation is critical !
???• Reinforcement Learning: fast but requires an efficient representation
• Evolutionary Robotics: low level representation, but slow…
11. 3. Development
Weng, J. (2004). Developmental robotics : Theory and experiments.
International Journal of Humanoid Robotics, 1(2), 199–236.
Autonomous development
12. 3. Development
Insights from psychology
The importance of redescribing knowledge representations
« A specifically human way to gain knowledge is for the mind to exploit
internally the information that it has already stored (both innate and
acquired), by redescribing its representations or, more precisely, by
iteratively re-representing in different representational formats what its
internal representations represent » [Karmiloff-Smith 1996]
When to restructure and consolidate knowledge ?
« Sleep consolidates recent memories and, concomitantly, could allow
insight by changing their representational structure. » [Wagner, 2004]
Kick-off meeting DREAM, Paris, 26/01/2015
13. Deferred Restructuring of Experience
in Autonomous Machines
H2020 FET Proactive « Knowing,
doing, being » 01/2015-12/2018
http://www.robotsthatdream.eu/
https://twitter.com/robotsthatdream
3. Development
Changing representations
Daytime
experience
(large batch)
Daytime
Consolidated knowledge
- task-relevant features
- task contexts
- abstract knowledge
- new motivations
No initial policy
No single task
Motivations:
- curiosity
- satisfying humans
- global mission
Behavior exploration
Knowledge improvement
Knowledge adaptation
Small
batch
Skill
Knowledge validation
Sequence of learning episodes driven by motivations
New situation:
-no reprogramming
-fast adaptation
Knowledge sharing
between robots:
- better generalization
- faster learning
Nighttime
Dream
Collective scale
Individual scale
Knowledge restructuring
Transfer from STM to LTM
14. Learning 10 to 100
times faster
Generates examples
of behaviours
Discrete actions
and sensors
to consider
Passive analysis
Representation
redescription
2
1
Learning
Direct policy search
(neuroevolution)
Task-agnostic
representations
Slow learning
Limited generalization
3
Learning
Discrete reinforcement
learning
Task-specific
representations
Fast learning
Good generalization
15. Development: bootstrapping simple manipulation skills
1. Day 1: sensori-motor babbling 2. «Night» Learning to manipulate an object in simulation
3. Day 2 : Back to reality
16. Thank you !
Questions ?
stephane.doncieux@upmc.fr
https://twitter.com/SDoncieux
http://people.isir.upmc.fr/doncieux