X. Wang and T. Dietterich. Efficient value function approximation using regression trees. In Proceedings of the IJCAI Workshop on Statistical Machine Learning for Large-Scale Optimization, 1999. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Multi-agent Q-learning and regression trees for automated.. - Sridharan, Tesauro (Correct)
....main contributions of this work are twofold. First, an important open question in Reinforcement Learning research is how to combine RL methods such as Qlearning with nonlinear function approximation. Most of the empirical research on this topic has involved neural networks. Our work, along with (Wang and Dietterich, 1999), is among the first to demonstrate success in combining Q learning with regression trees. Our results show clear advantages over the neural net approach, and thus provide impetus for further studies of tree based methods. The second contribution is that with regression trees, Q learning appears ....
X. Wang and T. G. Dietterich, "Efficient value function approximation using regression trees." Proceedings of: IJCAI-99 Workshop on Statistical Machine Learning for Large-Scale Optimization, Stockholm, Sweden, 31 Jul. 1999.
Empirical Comparison of Various Reinforcement.. - Abe, Pednault.. (2002) Self-citation (Wang) (Correct)
No context found.
X. Wang and T. Dietterich. Efficient value function approximation using regression trees. In Proceedings of the IJCAI Workshop on Statistical Machine Learning for Large-Scale Optimization, 1999.
Empirical Comparison of Various Reinforcement.. - Abe, Pednault.. Self-citation (Wang) (Correct)
....state space as a feature space, and the state space becomes prohibitively large to represent explicitly. For this reason, we employ reinforcement learning methods with function approximation, that is, we estimate and represent the value function as a function of state features and actions (e.g. [3, 14]) For this purpose, we employ the multivariate linear regression tree method implemented in the IBM ProbE data mining engine. 2.3. Direct (Batch) Reinforcement Learning Direct or batch reinforcement learning attempts to estimate the value function Q(s; a) by reformulating value iteration as a ....
X. Wang and T. Dietterich. Efficient value function approximation using regression trees. In Proceedings of the IJCAI Workshop on Statistical Machine Learning for Large-Scale Optimization, 1999.
Thesis Proposal: Learning to make decisions from large data sets - Zadrozny (Correct)
No context found.
X. Wang and T. G. Dietterich. Efficient value function approximation using regression trees. In J. Boyan, W. Buntine, and A. Jagota, editors, Statistical Machine Learning for Large Scale Optimization, Neural Computing Surveys, pages 51--54. 2000.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC