This paper presents a syntactic path-based learning algorithm (CANDEL from CANDIDATE-ELIMINATION) for the coreference resolution of pronouns that have their antecedents in the sam...
The paper explores a very simple agent design method called Q-decomposition, wherein a complex agent is built from simpler subagents. Each subagent has its own reward function and...
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
Doina Precup, Richard S. Sutton, Satinder P. Singh
Multimedia Data Mining requires the ability to automatically analyze and understand the content. The Community of Multimedia Agents project (COMMA) is devoted to creating an open ...
This article addresses collaborative learning in a multiagent system: each agent revises incrementally its beliefs B (a concept representation) to keep it consistent with the whol...
Gauvain Bourgne, Dominique Bouthinon, Amal El Fall...