Markov Decision Processes

Markov Decision Processes (MDPs) are a mathematical language for definiing the problem of making decisions over time using only the current observations and knowledge.

Our Papers on

    Other Papers on

      Our Papers on MDP

      1. PAC Optimal MDP Planning with Application to Invasive Species Management
        Taleghan, Majid Alkaee, Dietterich, Thomas G., Crowley, Mark, Hall, Kim, and Albers, H. Jo
        Journal of Machine Learning Research 2015
      2. Using equilibrium policy gradients for spatiotemporal planning in forest ecosystem management
        Crowley, Mark
        IEEE Transactions on Computers 2014
      3. PAC Optimal Planning for Invasive Species Management: Improved Exploration for Reinforcement Learning from Simulator-Defined MDPs
        Dietterich, Thomas G, Alkaee Taleghan, Majid, and Crowley, Mark
        In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-2013) 2013
      4. Policy gradient planning for environmental decision making with existing simulators
        Crowley, Mark, and Poole, David
        In Proceedings of the National Conference on Artificial Intelligence 2011
      5. thesis
        Equilibrium Policy Gradients for Spatiotemporal Planning
        Crowley, Mark
        2011
      6. Seeing the Forest Despite the Trees : Large Scale Spatial-Temporal Decision Making
        Crowley, Mark, Nelson, John, and Poole, David
        In Conference on Uncertainty in Artificial Intelligence (UAI09) 2009