Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Towards Information-Seeking Agents
Philip Bachman, Alessandro Sordoni, Adam Trischler
Nov 05, 2016 (modified: Dec 06, 2016)ICLR 2017 conference submissionreaders: everyone
Abstract:We develop a general problem setting for training and testing the ability of agents to gather information efficiently. Specifically, we present a collection of tasks in which success requires searching through a partially-observed environment, for fragments of information which can be pieced together to accomplish various goals. We combine deep architectures with techniques from reinforcement learning to develop agents that solve our tasks. We shape the behavior of these agents by combining extrinsic and intrinsic rewards. We empirically demonstrate that these agents learn to search actively and intelligently for new information to reduce their uncertainty, and to exploit information they have already acquired.
TL;DR:We investigate the behavior of models trained to answer questions by asking sequences of simple questions.
Conflicts:maluuba.com, mcgill.ca, umontreal.ca
Enter your feedback below and we'll get back to you as soon as possible.