Beruflich Dokumente
Kultur Dokumente
Pacman
Project
Group Overview
• Advisors:
– Jean Derks
– Pieter Spronck
• Group Members:
– Thomas Debray
– Yannick Soldati
– Anton Valkenberg
– Kalle Fischer
– Milad Memerian
– Michael Wiedau
Topics
• Project Overview
• Structure
• PDA
• GPS
• AI approaches
• Genetic Algorithms: basics
• Simulation
• Future Work
• Conclusion
Structure
PDA (Client)
GPS (Receiver)
How to get our position with the gps
receiver?
2 possible solutions
- Write the gps receiver software
(very long with a lot of mathematics)
- Use a framework
AI approaches
Defining interest to pacman
AI approaches
Defining interest to pacman
– E{tk} is the average number of simulation steps taken to kill PacMan over the N
games
– Max{tk} is the maximum tk over the N games
– p1 is a weighting parameter
– where
– p1 is a weighting parameter
AI approaches
Defining interest to pacman
AI approaches
Evolutionary, Rule-based approach
AI approaches
Cross-entropy approach
AI approaches
Cross-entropy approach
Potential
PotentialField
Field
• Mechanism to determine in which direction to
proceed
• System of peaks and trough
– Items conductive to game scoring having positive value
– Ghosts having negative values
• The values for those rewards and penalties can
be learned
• Leads Pacman to the peaks along the steepest
slopes
Neural
NeuralNetwork
Network
• Neural Networks are one more way to interpret the
situation
– Graph based representation of the map
– Each node has a feature vector
– values of those feature vectors are interpreted by the Neural
Network
• The weights for the NN are learned using an
evolutionary algorithm
• Performance is measured by taking the average score
of games
Neural
NeuralNetwork
Network
• The choice of the inputs to the NN is crucial
– Wrong choice places significant limitations on the
performance
Simulation
• Training environment
• Simplification external world
(map – movement – behavior)
• Input: starting positions, movement speed, AI
• Movement decided by AI advise
• Evolve through evolution
• Fitness calculation ~ scored points, elapsed time, ...
• Output: AI optimized parameters
Future work
• Start of programming the different modules
• AI programming
• GPS/PDA programming
• Simulation Environment
• Additional research
Conclusion
• Defined structure for the program
• Simulation environment
• PDA/GPS, GEO framework
• Research pacman-AI done
– Genetic approach
– Mathematical interest
Questions?