We consider the task of learning to accurately follow a trajectory in a vehicle such as a car or helicopter. A number of dynamic programming algorithms such as Differential Dynami...
J. Zico Kolter, Adam Coates, Andrew Y. Ng, Yi Gu, ...
In this paper we report an ethnographic study of workarounds--informal temporary practices for handling exceptions to normal workflow--in a hospital environment. Workarounds are a...
Marina Kobayashi, Susan R. Fussell, Yan Xiao, F. J...
Title of thesis: EFFICIENT AND ACCURATE STATISTICAL TIMING ANALYSIS FOR NON-LINEAR NON-GAUSSIAN VARIABILITY WITH INCREMENTAL ATTRIBUTES Ashish Dobhal, Master of Science, 2006 Thes...
Recent scaling up of decentralized partially observable Markov decision process (DEC-POMDP) solvers towards realistic applications is mainly due to approximate methods. Of this fa...
Many problems of multiagent planning under uncertainty require distributed reasoning with continuous resources and resource limits. Decentralized Markov Decision Problems (Dec-MDP...