2023 search results - page 376 / 405 » Human Agents and Intelligent Agents: An Experiment on the In... |
104
click to vote
SOCROB
2010
2010
Using the Interaction Rhythm as a Natural Reinforcement Signal for Social Robots: A Matter of Belief
14 years 10 months ago
Abstract. In this paper, we present the results of a pilot study of a human robot interaction experiment where the rhythm of the interaction is used as a reinforcement signal to le...
JAIR
2011
14 years 6 months ago
2011
Markovian processes have long been used to model stochastic environments. Reinforcement learning has emerged as a framework to solve sequential planning and decision-making proble...
ATAL
2007
Springer
15 years 6 months ago
2007
Springer
In this paper, we discuss the use of Targeted Trajectory Distribution Markov Decision Processes (TTD-MDPs)—a variant of MDPs in which the goal is to realize a specified distrib...
ATAL
2008
Springer
15 years 1 months ago
2008
Springer
Whether or not a critical threshold exists when epidemic diseases are spread in complex networks is a problem attracting attention from researchers in several disciplines. In 2001...
104
click to vote
AAAI
2004
15 years 1 months ago
2004
Traditionally, text classifiers are built from labeled training examples. Labeling is usually done manually by human experts (or the users), which is a labor intensive and time co...