Sciweavers

682 search results - page 136 / 137
» Autonomous Environment and Task Adaptation for Robotic Agent...
Sort
View
AIPS
2010
13 years 7 months ago
When Policies Can Be Trusted: Analyzing a Criteria to Identify Optimal Policies in MDPs with Unknown Model Parameters
Computing a good policy in stochastic uncertain environments with unknown dynamics and reward model parameters is a challenging task. In a number of domains, ranging from space ro...
Emma Brunskill
CCIA
2009
Springer
13 years 6 months ago
mWater: a Sandbox for Agreement Technologies
The management of natural resources is an intricate and consequential task. In particular, water management is at the forefront of public policy priorities in many countries becaus...
Antonio Garrido, Adriana Giret, Pablo Noriega
NN
2008
Springer
13 years 4 months ago
Multilayer in-place learning networks for modeling functional layers in the laminar cortex
Currently, there is a lack of general-purpose in-place learning networks that model feature layers in the cortex. By "general-purpose" we mean a general yet adaptive hig...
Juyang Weng, Tianyu Luwang, Hong Lu, Xiangyang Xue
IJACDT
2011
125views more  IJACDT 2011»
12 years 8 months ago
Becoming Creative through Self Observation: A (Second Order) Cybernetic Learning Strategy for the Metaverse
This study wishes to describe some of the key components of an art educational domain entitled ground<c>, which is being developed specifically for three dimensional online ...
Elif E. Ayiter
ATAL
2007
Springer
13 years 11 months ago
Model-based function approximation in reinforcement learning
Reinforcement learning promises a generic method for adapting agents to arbitrary tasks in arbitrary stochastic environments, but applying it to new real-world problems remains di...
Nicholas K. Jong, Peter Stone