Reinforcement Learning of Distributed Surveillance Plans

<p>This thesis describes the design and implementation of a Reinforcement Learning algorithm on a camera surveillance model which is used to know the stackelberg strategies of attacker and defender. This reinforcement learning algorithm is compared with the uniform policy and hill climbing algorithms by executing them on a common set of different data files, generated programmatically with various combinations of problem size, location, and orientation transitions as well as rewards of attacker and defender. The comparison includes the time taken to obtain better stackelberg policy and the resulted final pay-off of the defender. This thesis shows that the reinforcement learning algorithm developed in Java performs better than the uniform policy and proves to be chosen for large problem size as it produces acceptable results in less time when compared to that of the hill climbing algorithm. </p>

Name thesis:degree_name

Master of Science (MS)

Level thesis:degree_level

Masters Thesis

Discipline thesis:degree_discipline

Computing

Year dc:date.available

2014

Author dc:creator

• Chittireddy, Madhavi

Contributors dc:contributor

• Bikramjit Banerjee
• Beddhu Murali
• Dia Ali

• reinforcement learning
• stackleberg games
• multiagent
• attacker and defender
• randomized strategies
• AMPL
• Artificial Intelligence and Robotics

Repository record dc:identifier

https://aquila.usm.edu/masters_theses/75

OAI identifier oai:identifier

oai:aquila.usm.edu:masters_theses-1059