Sciweavers

908 search results - page 72 / 182
» Stochastic Finite Learning
Sort
View
ICML
2006
IEEE
14 years 9 months ago
PAC model-free reinforcement learning
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
Alexander L. Strehl, Lihong Li, Eric Wiewiora, Joh...
AIPS
2008
13 years 11 months ago
Stochastic Enforced Hill-Climbing
Enforced hill-climbing is an effective deterministic hillclimbing technique that deals with local optima using breadth-first search (a process called "basin flooding"). ...
Jia-Hong Wu, Rajesh Kalyanam, Robert Givan
ISMB
1994
13 years 10 months ago
Stochastic Motif Extraction Using Hidden Markov Model
In this paper, westudy the application of an ttMM(hidden Markov model) to the problem of representing protein sequencesby a stochastic motif. Astochastic protein motif represents ...
Yukiko Fujiwara, Minoru Asogawa, Akihiko Konagaya
NIPS
2008
13 years 10 months ago
Unlabeled data: Now it helps, now it doesn't
Empirical evidence shows that in favorable situations semi-supervised learning (SSL) algorithms can capitalize on the abundance of unlabeled training data to improve the performan...
Aarti Singh, Robert D. Nowak, Xiaojin Zhu
TSMC
2008
146views more  TSMC 2008»
13 years 8 months ago
Decentralized Learning in Markov Games
Learning Automata (LA) were recently shown to be valuable tools for designing Multi-Agent Reinforcement Learning algorithms. One of the principal contributions of LA theory is tha...
Peter Vrancx, Katja Verbeeck, Ann Nowé