34 search results - page 2 / 7 » Learning Policies for Embodied Virtual Agents through Demons... |
SIGECOM
2009
ACM
13 years 11 months ago
2009
ACM
Policy teaching considers a Markov Decision Process setting in which an interested party aims to influence an agent’s decisions by providing limited incentives. In this paper, ...
ATAL
2008
Springer
13 years 6 months ago
2008
Springer
Solutions to complex tasks often require the cooperation of multiple robots, however, developing multi-robot policies can present many challenges. In this work, we introduce teach...
ROMAN
2007
IEEE
13 years 10 months ago
2007
IEEE
— In this work, we further test the hypothesis that physical embodiment has a measurable effect on performance and impression of social interactions. Support for this hypothesis ...
AAAI
2010
13 years 5 months ago
2010
Bayesian inference is an appealing approach for leveraging prior knowledge in reinforcement learning (RL). In this paper we describe an algorithm for discovering different classes...
ATAL
2009
Springer
13 years 11 months ago
2009
Springer
This paper presents a model of neural network embodiment of intentions and planning mechanisms for autonomous agents. The model bridges the dichotomy of symbolic and non-symbolic ...