Christopher R. Mansley

Learn More
One of the key problems in reinforcement learning is balancing exploration and exploitation. Another is learning and acting in large or even continuous Markov decision processes (MDPs), where compact function approximation has to be used. In this paper, we provide a practical solution to exploring large MDPs by integrating a powerful exploration technique,(More)
In this paper, we present a new algorithm that integrates recent advances in solving continuous bandit problems with sample-based rollout methods for planning in Markov Decision Processes (MDPs). Our algorithm , Hierarchical Optimistic Optimization applied to Trees (HOOT) addresses planning in continuous action MDPs, directing the exploration of the search(More)
We describe an inexpensive robot that serves as a physical autonomic element, capable of navigating, mapping and monitoring data centers with little or no human involvement, even ones that it has never seen before. Through a series of real experiments and simulations, we establish that the robot is sufficiently accurate, efficient and robust to be of(More)
Based on the same principles as a single-rotor helicopter, a quadrotor is a flying vehicle that is propelled by four horizontal blades surrounding a central chassis. Because of this vehicle's symmetry and propulsion mechanism, a quadrotor is capable of simultaneously moving and steering by simple modulation of motor speeds [1]. This stability and relative(More)
We describe an inexpensive autonomous robot capable of navigating previously unseen data centers and monitoring key metrics such as air temperature<sup>1</sup>. The robot provides real-time navigation and sensor data to commercial IBM software, thereby enabling real-time generation of the data center layout, a thermal map and other visualizations of energy(More)
Terrain classification in robotics has heavily focused on determining a region for traversal, while also labeling obstacles. Our work attempts to expand this essentially binary viewpoint and to use terrain classifiers as an indicator for different system dynamics. By learning multiple models of the system dynamics , the robot is able to assess alternative(More)
In this paper, we develop a suite of motion planning strategies suitable for large-scale sensor networks. These solve the problem of reconfiguring the network to a new shape while minimizing either the total distance traveled by the nodes or the maximum distance trav-eled by any node. Three network paradigms are investigated: centralized, computationally(More)
Acknowledgment First, I would like to thank my advisor, John Spletzer, whose patience and experience I could not have done without. I would also like to thank Jason Derenick, who made me appreciate the simplicity and beauty of mathematics and would always answer my questions, no matter how quaint. If it were not for Chris Thorne, I would have never been(More)
  • 1