Accelerating reinforcement learning through implicit imitation
B Price, C Boutilier - Journal of Artificial Intelligence Research, 2003 - jair.org
Imitation can be viewed as a means of enhancing learning in multiagent environments. It
augments an agent's ability to learn useful behaviors by making intelligent use of the …
augments an agent's ability to learn useful behaviors by making intelligent use of the …
[PDF][PDF] 11 A Bayesian model of imitation in infants and robots
Humans are often characterized as the most behaviourally flexible of all animals. Evolution
has stumbled upon an unlikely but very effective trick for achieving this state. Relative to …
has stumbled upon an unlikely but very effective trick for achieving this state. Relative to …
Imitation with ALICE: Learning to imitate corresponding actions across dissimilar embodiments
A Alissandrakis, CL Nehaniv… - IEEE Transactions on …, 2002 - ieeexplore.ieee.org
Imitation is a powerful mechanism whereby knowledge may be transferred between agents
(both biological and artificial). Key problems on the topic of imitation have emerged in …
(both biological and artificial). Key problems on the topic of imitation have emerged in …
Confidence-based multi-robot learning from demonstration
S Chernova, M Veloso - International Journal of Social Robotics, 2010 - Springer
Learning from demonstration algorithms enable a robot to learn a new policy based on
demonstrations provided by a teacher. In this article, we explore a novel research direction …
demonstrations provided by a teacher. In this article, we explore a novel research direction …
A cognitive model of imitative development in humans and machines
AP Shon, JJ Storz, AN Meltzoff… - International Journal of …, 2007 - World Scientific
Several algorithms and models have recently been proposed for imitation learning in
humans and robots. However, few proposals offer a framework for imitation learning in noisy …
humans and robots. However, few proposals offer a framework for imitation learning in noisy …
Synchrony and perception in robotic imitation across embodiments
A Alissandrakis, CL Nehaniv… - Proceedings 2003 IEEE …, 2003 - ieeexplore.ieee.org
Social robotics opens up the possibility of individualized social intelligence in member
robots of a community, and allows us to harness not only individual learning by the …
robots of a community, and allows us to harness not only individual learning by the …
Incremental learning and memory consolidation of whole body human motion primitives
D Kulić, Y Nakamura - Adaptive Behavior, 2009 - journals.sagepub.com
The ability to learn during continuous and on-line observation would be advantageous for
humanoid robots, as it would enable them to learn during co-location and interaction in the …
humanoid robots, as it would enable them to learn during co-location and interaction in the …
[PDF][PDF] The role of population dynamics in imitation
We propose an extension of the study of imitation in artefacts in which imitation takes place
at the populationlevel. Instead of assuming a one-to-one teacher-student relation between …
at the populationlevel. Instead of assuming a one-to-one teacher-student relation between …
[PDF][PDF] Emerging shared action categories in robotic agents through imitation
In this paper we present our work on developing a shared repertoire of action categories
through imitation. A population of robotic agents invents and shares a repertoire of action …
through imitation. A population of robotic agents invents and shares a repertoire of action …
An imitation game for emerging action categories
B Jansen - European Conference on Artificial Life, 2003 - Springer
An imitation game for learning action categories is proposed. It serves to invent and share a
repertoire of action categories in a population of robotic agents. The agents start without any …
repertoire of action categories in a population of robotic agents. The agents start without any …