game theory, social interactions and artificial intelligence supervisor: philip sterne supervisee:...

14
Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

Upload: stephanie-stanley

Post on 29-Jan-2016

214 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

Game Theory, Social Interactions and Artificial Intelligence

Supervisor: Philip SterneSupervisee: John Richter

Page 2: Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

Contents

● Quick and Dirty Summary● Outline of Game Theory● Outline of Algorithms used● Discussion of Feasability● Implementation Details● Readings and Sources of Information● Proposed Timeline● Questions

Page 3: Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

Quick and Dirty Summary

Using a variety of artificial intelligence techniques to develop optimal

strategies for participants to use in situations where some combination of

competition and cooperation are necessary.

Page 4: Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

Game Theory

● Prisoner's Dilemma● Simple

– Only two participants– Only two choices

● Because of simplicity, it is trivial to consider all possible eventualities

“The Evolution of Cooperation”, Robert Axelrod, Basic Books, 1984

Page 5: Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

Artificial Intelligence

● Emulating features of human intellect● Particularly useful for solving non-trivial

problems– function maximization, optimization

● Contemporary AI forms:– Expert systems, Case-based reasoning– Neural Networks– Genetic Algorithms– Reinforcement Learning

Page 6: Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

AI: Artificial Neural Networks

● Modelling the actual structure of the human brain

● The neurons making up the map use weights and thresholds to emulate a complex function

● The map itself is quite complex to create, with neuron layers of various sizes connected together

● Of minor use in my project

Page 7: Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

AI: Genetic Algorithms

● Used to maximize functions● “Breeds” the best solutions● Uses crossover (joining solutions at

random points), mutation (occasionally changing a random value to something else to ensure global maximum found) on a variety of sub-optimal solutions to encourage the best of them to breed, and results in the next generation representing better solutions

Page 8: Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

AI: Reinforcement Learning

● Most recent of these AI's● Similar to GA's

– approaches best solution● Unlike GA's

– learning happens during the agents life, not (always) passed on to the children

● Uses reward/punishment system to encourage agents to take best strategies, while still encouraging discovery and innovation

“Reinforcement Learning, an Introduction”, Sutton and Barto, MIT Press, 1998

Page 9: Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

Less Quick, Less Dirty Summary

Using genetic algorithms and reinforcement learning to train neural

nets in agents in order to model complex game theory, and developing optimal strategies for real-world games

Page 10: Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

Feasability

● Is the project too small?– Can be extended by testing other AI

approaches and combinations– Can be used to model a variety of

scenarios● Is the project too big?

– Three distinct portions can be simplified: ANN's, GA's and RL.

– Simplify the test model to use less variables, less complex ANN's

Page 11: Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

Implementation

● No specific languages or platforms are required or recommended for developing AI

● Thus, I choose the route of free software and mainstream languages, and shall write the program for the GNU/Linux platform, in C++

Page 12: Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

Further Resources and Reading

● JASSS, Journal of Artificial Societies and Social Simulation [http://jass.soc.surrey.ac.uk/JASSS.html]

● “Design, Evaluation and Comparison of Evolution and Reinforcement Learning Models”, Clinton Brett McLean (2001)

● Game Theory.Net [http://www.gametheory.net]

● Hours and hours of playing games in the labs. No, really.

Page 13: Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

Timeline

Creating Agent Construct 2 weeks

Creating Environment and Rules 2 weeks

Integrating Agent and Environment 1 week

Testing Learning and Genetic Algorithms 2 weeks

Strategy Development 2 weeks

Extensions 2 to 5 weeks

Page 14: Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter

Questions

● To maintain order, could I request questions in phases:– AI algorithms or techniques– Game theory– Integration– Feasability and implementation of project