34 search results - page 4 / 7 » Learning Policies for Embodied Virtual Agents through Demons... |
ECML
2004
Springer
13 years 11 months ago
2004
Springer
Abstract. We investigate the problem of using function approximation in reinforcement learning where the agent’s policy is represented as a classifier mapping states to actions....
IIE
2007
13 years 5 months ago
2007
We investigate the possibility to apply a known machine learning algorithm of Q-learning in the domain of a Virtual Learning Environment (VLE). It is important in this problem doma...
ATAL
2006
Springer
13 years 9 months ago
2006
Springer
RVRL (Rule Value Reinforcement Learning) is a new algorithm which extends an existing learning framework that models the environment of a situated agent using a probabilistic rule...
ROBOCUP
2007
Springer
13 years 11 months ago
2007
Springer
Reinforcement learning is a paradigm under which an agent seeks to improve its policy by making learning updates based on the experiences it gathers through interaction with the en...
IAT
2008
IEEE
13 years 5 months ago
2008
IEEE
While context-awareness has been found to be effective for decision support in complex domains, most of such decision support systems are hard-coded, incurring significant develop...