Motivated Learning based on Goal Creation

1. Motivated Learning based on Goal Creation Janusz Starzyk School of Electrical Engineering and Computer Science, Ohio University, USA www.ent.ohiou.edu/~starzyk Istituto Dalle Molle di Studi sull'Intelligenza Artificiale, 4 December 2009.

2. Outline • Embodied Intelligence (EI) • Embodiment of Mind • How to Motivate a Machine • Goal Creation Hierarchy • GCS Experiment • Motivated Learning

3. Design principles of intelligent systems from Rolf Pfeifer “Understanding of Intelligence”, 1999 • Interaction with complex environment • cheap design • ecological balance • redundancy principle • parallel, loosely coupled processes • asynchronous • sensory-motor coordination • value principle Agent Drawing by Ciarán O’Leary- Dublin Institute of Technology

4. Embodied Intelligence • Definition • Embodied Intelligence (EI) is a mechanism that learns how to survive in a hostile environment • Mechanism: biological, mechanical or virtual agent with embodied sensors and actuators • EI acts on environment and perceives its actions • Environment hostility is persistent and stimulates EI to act • Hostility: direct aggression, pain, scarce resources, etc • EI learns so it must have associative self-organizing memory • Knowledge is acquired by EI

5. Embodiment of a Mind • Embodiment is a part of environment under control of the mind • It contains intelligence core and sensory motor interfaces to interact with environment • It is necessary for development of intelligence • It is not necessarily constant

6. Embodiment of Mind • Changes in embodiment modify brain’s self-determination • Brain learns its own body’s dynamics • Self-awareness is a result of identification with own embodiment • Embodiment can be extended by using tools and machines • Successful operation is a function of correct perception of environment and own embodiment

7. How to Motivate a Machine ? A fundamental question is what motivates an agent to do anything, and in particular, to enhance its own complexity? What drives an agent to explore the environment and learn ways to effectively interact with it?

8. How to Motivate a Machine ? • Pfeifer claims that an agent’s motivation should emerge from the developmentalprocess. • He called this the “motivated complexity” principle. • Chicken and egg problem? An agent must have a motivation to develop while his motivation comes from development? • Steels suggested equipping an agent with self-motivation. • “Flow” experienced when people perform their expert activity well would motivate to accomplish even more complex tasks. • But what is the mechanism of “flow”? • Oudeyer proposed an intrinsic motivation system. • Motivation comes from a desire to minimize the prediction error. • Similar to “artificial curiosity” presented by Schmidhuber.

9. How to Motivate a Machine ? • Although artificial curiosity helps to explore the environment, it leads to learning without a specific purpose. • It may be compared to exploration in reinforcement learning. • Exploration is needed in order to learn and to model the environment. • But is exploration the only motivation we need to develop EI? • Can we find a more efficient mechanism for learning? • I suggest a simpler mechanism to motivate a machine.

10. How to Motivate a Machine ? • I suggest that it is the hostility of the environment, in the definition of EI that is the most effective motivational factor. • It is the pain we receive that moves us. • It is our intelligence determined to reduce this pain that motivates us to act, learn, and develop. • Both are needed - hostility of the environment and intelligence that learns how to reduce the pain. • Thus pain is good. • Without pain we would not be motivated to develop. Fig. englishteachermexico.wordpress.com/

11. Motivated Learning • I suggest a goal-driven mechanism to motivate a machine to act, learn, and develop. • A simple pain based goal creation system. • It uses externally defined pain signals that are associated with primitive pains. • Machine is rewarded for minimizing the primitive pain signals. • Definition: Motivated learning (ML) is learning based on the self-organizing system of goal creation in embodied agent. • Machine creates abstract goals based on the primitive pain signals. • It receives internal rewards for satisfying its goals (both primitive and abstract). • ML applies to EI working in a hostile environment.

12. Pain-center and Goal Creation • Simple Mechanism • Creates hierarchy • of values • Leads to formulation • of complex goals • Reinforcement • Pain increase • Pain decrease • Forces exploration

13. Sensory pathway Motor pathway (perception, sense) (action, reaction) refrigerator Open Level II - + “ food ” becomes a Abstract pain sensory input to (Delayed memory of pain) abstract pain center Food Eat Level I - + Dual pain Pain Primitive Level Stomach Association Inhibition Reinforcement Connection Planning Expectation Abstract Goal Creation for ML • The goal is to reduce theprimitive pain level • Abstract goalsare created if they satisfy the primitive goals

14. Goal Creation Experiment Sensory-motor pairs and their effect on the environment

15. Goal Creation Experiment in ML Pain signals in GCS simulation

16. Goal Creation Experiment in ML Action scatters in 5 GCS simulations

17. Goal Creation Experiment in ML The average pain signals in 100 GCS simulations

18. Mean primitive pain Pp value as a function of the number of iterations: • - green line for TDF • blue line for GCS. • Primitive pain ratio with pain threshold 0.1 Compare RL (TDF) and ML (GCS)

19. Problem solved Compare RL (TDF) and ML (GCS) • Comparison of execution time on log-log scale • TD-Falcon green • GCS blue • Combined efficiency of GCS 1000 better than TDF Conclusion: embodied intelligence, with motivated learning based on goal creation is an effective learning and decision making system for dynamic environments.

20. Single value function Measurable rewards Can be optimized Predictable Objectives set by designer Maximizes the reward Potentially unstable Learning effort increases with complexity Always active Multiple value functions One for each goal Internal rewards Cannot be optimized Unpredictable Sets its own objectives Solves minimax problem Always stable Learns better in complex environment than RL Acts when needed Reinforcement Learning Motivated Learning

21. Sounds like science fiction • If you’re trying to look far ahead, and what you see seems like science fiction, it might be wrong. • But if it doesn’t seem like science fiction, it’s definitely wrong. From presentation by Feresight Institute

22. Questions?

23. Resources – Evolution of Electronics From Ray Kurzwail, The Singularity Summit at Stanford, May 13, 2006

24. By Gordon E. Moore

26. Clock Speed (doubles every 2.7 years) From Ray Kurzwail, The Singularity Summit at Stanford, May 13, 2006

27. Doubling (or Halving) times • Dynamic RAM Memory “Half Pitch” Feature Size 5.4 years • Dynamic RAM Memory (bits per dollar) 1.5 years • Average Transistor Price 1.6 years • Microprocessor Cost per Transistor Cycle 1.1 years • Total Bits Shipped 1.1 years • Processor Performance in MIPS 1.8 years • Transistors in Intel Microprocessors 2.0 years • Microprocessor Clock Speed 2.7 years From Ray Kurzwail, The Singularity Summit at Stanford, May 13, 2006

28. From Ray Kurzwail, The Singularity Summit at Stanford, May 13, 2006

29. From Hans Moravec, Robot, 1999

30. Sequential Error prone Require programming Low cost Well developed programming methods Concurrent Robust Require design Significant cost Hardware prototypes hard to build Software or hardware? Software Hardware

31. Future software/hardware capabilities Human brain complexity

32. Why should we care? Source: SEMATECH

33. Design Productivity Gap  Low-Value Designs? Percent of die area that must be occupied by memory to maintain SOC design productivity Source = Japanese system-LSI industry

34. Self-Organizing Learning Arrays SOLAR • * Self-organization • * Sparse and local interconnections • * Dynamically reconfigurable • * Online data-driven learning • Integrated circuits connect transistors into a system • millions of transistors easily assembled • first 50 years of microelectronic revolution • Self-organizing arrays connect processors into a system • millions of processors easily assembled • next 50 years of microelectronic revolution