PLOW: A Collaborative Task Learning Agent

13 years 6 months ago

Download www.cs.rochester.edu

To be effective, an agent that collaborates with humans needs to be able to learn new tasks from humans they work with. This paper describes a system that learns executable task models from a single collaborative learning session consisting of demonstration, explanation and dialogue. To accomplish this, the system integrates a range of AI technologies: deep natural language understanding, knowledge representation and reasoning, dialogue systems, planning/agent-based systems and machine learning. A formal evaluation shows the approach has great promise.

James F. Allen, Nathanael Chambers, George Ferguso

Real-time Traffic

AAAI 2007 | Collaborative Learning Session | Deep Natural Language | Executable Task Models | Intelligent Agents |

claim paper

» Collaborative multiagent learning for classification tasks

» Collaborative Agent Learning Using Neurocomputing

» COLLAGEN When Agents Collaborate with People

» SelfOrganizing Cognitive Agents and Reinforcement Learning in MultiAgent Environment

» Groups of Collaborating Users and Agents in Ambient Intelligent Environments

» Transfer Learning in Collaborative Filtering with Uncertain Ratings

» RealTime Collaborative Planning with the Crowd

» Building a Collaborative Information Agent in a HomeBot Application

Post Info
More Details (n/a)

Added	02 Oct 2010
Updated	02 Oct 2010
Type	Conference
Year	2007
Where	AAAI
Authors	James F. Allen, Nathanael Chambers, George Ferguson, Lucian Galescu, Hyuckchul Jung, Mary D. Swift, William Taysom

Comments (0)

Sciweavers

PLOW: A Collaborative Task Learning Agent

AAAI 2007 | Collaborative Learning Session | Deep Natural Language | Executable Task Models | Intelligent Agents |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers