README

Implementation of a high-performance adaptive queueing simulation
environment, which can be configured to run on clusters of computers
using MPI. The underlying simulator is based on advanced data
structures to provide efficient event handling, such as a priority
queue implementation geared towards discrete event simulation
[1]. Decentralised control is implemented using SARSA reinforcement
learning with a neural network function approximator to provide
compact representation of the state space. Details and results of the
research into adaptive queueing systems can be found [2-5].


[1] Ladder queue: An <i>O</i>(1) priority queue structure for
    large-scale discrete event simulation
    by: Wai T. Tang, Rick, Ian L. Thng
    ACM Transactions on Modeling and Computer Simulation (TOMACS),
    Vol. 15, No. 3. (July 2005), pp. 175-204,
    doi:10.1145/1103323.1103324

 	
[2] Cognitive Policy Learner: Biasing Winning or Losing Strategies
    by Dominik Dahlem, Jim Dowling, William Harrison
    In Tenth International Conference on Autonomous Agents and
    Multiagent Systems (2--6 May 2011), pp. 601-608

[3] Collaborative Function Approximation in Social Multiagent Systems
    by Dominik Dahlem, William Harrison
    Web Intelligence and Intelligent Agent Technology, IEEE/WIC/ACM
    International Conference on In Web Intelligence and Intelligent
    Agent Technology, IEEE/WIC/ACM International Conference on
    (September 2010), pp. 48-55, doi:10.1109/WI-IAT.2010.276

[4] Globally Optimal Multi-agent Reinforcement Learning Parameters in
    Distributed Task Assignment
    by Dominik Dahlem, William Harrison
    Web Intelligence and Intelligent Agent Technology, IEEE/WIC/ACM
    International Conference on In Web Intelligence and Intelligent
    Agent Technology, IEEE/WIC/ACM International Conference on, Vol. 2
    (2009), pp. 28-35, doi:10.1109/wi-iat.2009.122

[5] Waiting Time Sensitivities of Social and Random Graph Models
    by Dominik Dahlem, William Harrison
    Social Network Analysis and Mining, International Conference on
    Advances in In Social Network Analysis and Mining, International
    Conference on Advances in, Vol. 0 (July 2009), pp. 176-181,
    doi:10.1109/asonam.2009.25