Sciweavers

3523 search results - page 165 / 705
» Feature interaction in policies
Sort
View
SIGDOC
2009
ACM
16 years 1 months ago
Formalization and community investment in wikipedia's regulating texts: the role of essays
This poster presents ongoing research on how discursive and editing behaviors are regulated on Wikipedia by means of documented rules and practices. Our analysis focuses on three ...
Jonathan T. Morgan, Katie Derthick, Toni Ferro, El...
ROBOCUP
2007
Springer
153views Robotics» more  ROBOCUP 2007»
16 years 18 days ago
Model-Based Reinforcement Learning in a Complex Domain
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...
Shivaram Kalyanakrishnan, Peter Stone, Yaxin Liu
GECCO
2006
Springer
133views Optimization» more  GECCO 2006»
15 years 10 months ago
On-line evolutionary computation for reinforcement learning in stochastic domains
In reinforcement learning, an agent interacting with its environment strives to learn a policy that specifies, for each state it may encounter, what action to take. Evolutionary c...
Shimon Whiteson, Peter Stone
JSW
2007
191views more  JSW 2007»
15 years 6 months ago
Building Self-Configuring Data Centers with Cross Layer Coevolution
Abstract—This paper describes a biologically-inspired architecture, called SymbioticSphere, which allows data centers to autonomously adapt to dynamic environmental changes. Symb...
Paskorn Champrasert, Junichi Suzuki
ICMCS
2010
IEEE
154views Multimedia» more  ICMCS 2010»
15 years 4 months ago
Minimizing delay in lossless sequential data streaming
There is an ongoing explosion of interactive Internet applications. By nature, these applications require responsive clientserver data exchange and lossless, in-order delivery. In...
Sanjeev Mehrotra, Jin Li, Ying-zong Huang