Sciweavers

89 search results - page 7 / 18
» Learning with Continuous Experts Using Drifting Games
Sort
View
IAT
2006
IEEE
14 years 2 months ago
Resolution-Based Policy Search for Imperfect Information Differential Games
Differential games (DGs), considered as a typical model of game with continuous states and non-linear dynamics, play an important role in control and optimization. Finding optimal...
Minh Nguyen-Duc, Brahim Chaib-draa
NIPS
2000
13 years 10 months ago
Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task
The problem of reinforcement learning in large factored Markov decision processes is explored. The Q-value of a state-action pair is approximated by the free energy of a product o...
Brian Sallans, Geoffrey E. Hinton
EUSFLAT
2009
136views Fuzzy Logic» more  EUSFLAT 2009»
13 years 6 months ago
Fuzzy Continuous Evaluation in Training Systems Based on Virtual Reality
The approach of continuous evaluation is an important tool in the learning process. However, only recently it was applied in training based on virtual reality. This paper presents ...
Ronei Moraes, Liliane Machado
COR
2008
142views more  COR 2008»
13 years 8 months ago
Application of reinforcement learning to the game of Othello
Operations research and management science are often confronted with sequential decision making problems with large state spaces. Standard methods that are used for solving such c...
Nees Jan van Eck, Michiel C. van Wezel
CG
2008
Springer
13 years 10 months ago
Learning Positional Features for Annotating Chess Games: A Case Study
Abstract. By developing an intelligent computer system that will provide commentary of chess moves in a comprehensible, user-friendly and instructive way, we are trying to use the ...
Matej Guid, Martin Mozina, Jana Krivec, Aleksander...