Sciweavers

343 search results - page 17 / 69
» Action discovery for reinforcement learning
Sort
View
CORR
2007
Springer
73views Education» more  CORR 2007»
13 years 7 months ago
Universal Reinforcement Learning
—We consider an agent interacting with an unmodeled environment. At each time, the agent makes an observation, takes an action, and incurs a cost. Its actions can influence futu...
Vivek F. Farias, Ciamac Cyrus Moallemi, Tsachy Wei...
AIED
2005
Springer
14 years 1 months ago
Discovery of Patterns in Learner Actions
This paper describes an approach for analysis of computer-supported learning processes utilizing logfiles of learners’ actions. We provide help to researchers and teachers in ...
Andreas Harrer, Michael Vetter, Stefan Thür, ...
ICML
2007
IEEE
14 years 8 months ago
Conditional random fields for multi-agent reinforcement learning
Conditional random fields (CRFs) are graphical models for modeling the probability of labels given the observations. They have traditionally been trained with using a set of obser...
Xinhua Zhang, Douglas Aberdeen, S. V. N. Vishwanat...
UAI
2008
13 years 9 months ago
Model-Based Bayesian Reinforcement Learning in Large Structured Domains
Model-based Bayesian reinforcement learning has generated significant interest in the AI community as it provides an elegant solution to the optimal exploration-exploitation trade...
Stéphane Ross, Joelle Pineau
27
Voted
HIS
2008
13 years 9 months ago
New Crossover Operator for Evolutionary Rule Discovery in XCS
XCS is a learning classifier system that combines a reinforcement learning scheme with evolutionary algorithms to evolve rule sets on-line by means of the interaction with an envi...
Sergio Morales-Ortigosa, Albert Orriols-Puig, Este...