Adrian K. Agogino

I am a researcher with the Robust Software Engineering Group in the Intelligent Systems Division at NASA Ames Research Center, employed through the University of California, Santa Cruz.

My research interests are in the fields of machine learning, complex learning systems and multiagent control. My early work includes novel visualization methods for complex systems and ways to better adapt evolutionary algorithms to multiagent online environments. More recent work includes using reinforcement learning in multiagent systems. Since 2004 I have been working on complex systems projects including air traffic flow management, rocket engine analysis, and coordination in multi-rover learning.  My publications focus on the fields of machine learning, multiagent systems, reinforcement learning, evolutionary systems and visualization of complex systems.

Representative publications

• Agent-Based Resource Allocation in Dynamically Formed CubeSat Constellations. C. HolmesParker, A. Agogino, In Proceedings of the Tenth International Joint Conference on Autonomous Agents and Multiagent Systems, 2011.
• A Multiagent Approach to Managing Air Traffic Flow. K. Tumer and A. K. Agogino. Journal of Autonomous Agents and Multi-Agent Systems, 2010.
• Improving Air Traffic Management with A Learning Multiagent System, K. Tumer and A. K. Agogino,  Intelligent Systems, 24(1), IEEE, Computer Society, 2009.
• Multiagent Learning for Black Box System Reward Functions, K. Tumer and A. K. Agogino, Advances in Complex Systems, 2009.
• Analyzing and Visualizing Multiagent Rewards in Dynamic and Stochastic Environments, A. K. Agogino and K. Tumer, Journal of Autonomous Agents and Multi Agent Systems 2008.
• Distributed Agent-Based Air Traffic Flow Management, K. Tumer and A. Agogino., In Proceedings of the Sixth International Joint Conference on Autonomous Agents and Multiagent Systems, 2007. Best paper award (Out of 531 submissions)
• Entropy Based Anomaly Detection Applied to Space Shuttle Main Engines, A. Agogino and K. Tumer, In Proceedings of the IEEE Aerospace Conference, 2006.
• QUICR-Learning for Multiagent Coordination, A. Agogino and K. Tumer, In Proceedings of the 21st National Conference on Artificial Intelligence, 2006.
• Distributed Evaluation Functions for Fault Tolerant Multi Rover Systems, A. Agogino and K. Tumer, In Proceedings of the Genetic and Evolutionary Computation Conference, July 2006.
• A Distributed and Adaptive Health and Mission Management Architecture, K. Tumer, S. Uckun, and A. Agogino, In Integrated Systems Health Management, 2005.