Sciweavers

3084 search results - page 201 / 617
» Learning to Take Actions
Sort
View
124
Voted
TSMC
2002
98views more  TSMC 2002»
15 years 4 months ago
The STAR automaton: expediency and optimality properties
Abstract--We present the STack ARchitecture (STAR) automaton. It is a fixed structure, multiaction, reward-penalty learning automaton, characterized by a star-shaped state transiti...
Anastasios A. Economides, Athanasios Kehagias
NN
2007
Springer
105views Neural Networks» more  NN 2007»
15 years 4 months ago
Guiding exploration by pre-existing knowledge without modifying reward
Reinforcement learning is based on exploration of the environment and receiving reward that indicates which actions taken by the agent are good and which ones are bad. In many app...
Kary Främling
CORR
2012
Springer
216views Education» more  CORR 2012»
14 years 8 days ago
Fractional Moments on Bandit Problems
Reinforcement learning addresses the dilemma between exploration to find profitable actions and exploitation to act according to the best observations already made. Bandit proble...
Ananda Narayanan B., Balaraman Ravindran
162
Voted
JMLR
2012
13 years 7 months ago
Hierarchical Relative Entropy Policy Search
Many real-world problems are inherently hierarchically structured. The use of this structure in an agent’s policy may well be the key to improved scalability and higher performa...
Christian Daniel, Gerhard Neumann, Jan Peters
CVPR
2000
IEEE
16 years 6 months ago
Multimodal Speaker Detection Using Error Feedback Dynamic Bayesian Networks
Design and development of novel human-computer interfaces poses a challenging problem: actions and intentions of users have to be inferred from sequences of noisy and ambiguous mu...
Vladimir Pavlovic, James M. Rehg, Ashutosh Garg, T...