Sciweavers

AAAI
2015
10 years 1 months ago
UT Austin Villa 2014: RoboCup 3D Simulation League Champion via Overlapping Layered Learning
Layered learning is a hierarchical machine learning paradigm that enables learning of complex behaviors by incrementally learning a series of sub-behaviors. A key feature of layer...
Patrick MacAlpine, Mike Depinet, Peter Stone
AAAI
2015
10 years 1 months ago
Planned Protest Modeling in News and Social Media
Civil unrest (protests, strikes, and “occupy” events) is a common occurrence in both democracies and authoritarian regimes. The study of civil unrest is a key topic for politi...
Sathappan Muthiah, Bert Huang, Jaime Arredondo, Da...
AAAI
2015
10 years 1 months ago
Robot Learning Manipulation Action Plans by "Watching" Unconstrained Videos from the World Wide Web
In order to advance action generation and creation in robots beyond simple learned schemas we need computational tools that allow us to automatically interpret and represent human...
Yezhou Yang, Yi Li, Cornelia Fermüller, Yiann...
AAAI
2015
10 years 1 months ago
Assessing the Robustness of Cremer-McLean with Automated Mechanism Design
In a classic result in the mechanism design literature, Cremer and McLean (1985) show that if buyers’ valuations are sufficiently correlated, a mechanism exists that allows the...
Michael Albert, Vincent Conitzer, Giuseppe Lopomo
AAAI
2015
10 years 1 months ago
Measuring Plan Diversity: Pathologies in Existing Approaches and A New Plan Distance Metric
In this paper we present a plan-plan distance metric based on Kolmogorov (Algorithmic) complexity. Generating diverse sets of plans is useful for tasks such as probing user prefer...
Robert P. Goldman, Ugur Kuter