Sciweavers

170 search results - page 4 / 34
» Learning to play Tetris applying reinforcement learning meth...
Sort
View
SARA
2005
Springer
15 years 3 months ago
Feature-Discovering Approximate Value Iteration Methods
Sets of features in Markov decision processes can play a critical role ximately representing value and in abstracting the state space. Selection of features is crucial to the succe...
Jia-Hong Wu, Robert Givan
ICML
2003
IEEE
15 years 2 months ago
The Significance of Temporal-Difference Learning in Self-Play Training TD-Rummy versus EVO-rummy
Reinforcement learning has been used for training game playing agents. The value function for a complex game must be approximated with a continuous function because the number of ...
Clifford Kotnik, Jugal K. Kalita
ROBOCUP
2007
Springer
167views Robotics» more  ROBOCUP 2007»
15 years 3 months ago
Cooperative/Competitive Behavior Acquisition Based on State Value Estimation of Others
The existing reinforcement learning approaches have been suffering from the curse of dimension problem when they are applied to multiagent dynamic environments. One of the typical...
Kentarou Noma, Yasutake Takahashi, Minoru Asada
AR
2008
118views more  AR 2008»
14 years 9 months ago
Efficient Behavior Learning Based on State Value Estimation of Self and Others
The existing reinforcement learning methods have been seriously suffering from the curse of dimension problem especially when they are applied to multiagent dynamic environments. ...
Yasutake Takahashi, Kentarou Noma, Minoru Asada
ML
1998
ACM
136views Machine Learning» more  ML 1998»
14 years 9 months ago
Co-Evolution in the Successful Learning of Backgammon Strategy
Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...
Jordan B. Pollack, Alan D. Blair