Decentralized reinforcement learning (DRL) has been applied to a number of distributed applications. However, one of the main challenges faced by DRL is its convergence. Previous ...
Chongjie Zhang, Victor R. Lesser, Sherief Abdallah
We study the expressiveness of a positive fragment of path queries, denoted Path+ , on node-labeled trees documents. The expressiveness of Path+ is studied from two angles. First, ...
Yuqing Wu, Dirk Van Gucht, Marc Gyssens, Jan Pared...
We propose a novel extraction approach that exploits content redundancy on the web to extract structured data from template-based web sites. We start by populating a seed database...
Pankaj Gulhane, Rajeev Rastogi, Srinivasan H. Seng...
To complement standard fitness functions, we propose "Fitness Importance" (FI) as a novel meta-heuristic for online learning systems. We define FI and show how it can be...
The rapid adoption of mobile devices that are able to capture and transmit a wide variety of sensing modalities (media and location) has enabled a new data collection paradigm - p...
Sasank Reddy, Deborah Estrin, Mark H. Hansen, Mani...