State Similarity Based Approach for Improving Performance in RL

Date

2007-01-12

Author

Girgin, Sertan
Polat, Faruk
Alhajj, Reda

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

43
views

0
downloads

This paper employs state similarity to improve reinforcement learning performance. This is achieved by first identifying states with similar sub-policies. Then, a tree is constructed to be used for locating common action sequences of states as derived from possible optimal policies. Such sequences are utilized for defining a similarity function between states, which is essential for reflecting updates on the action-value function of a state onto all similar states. As a result, the experience acquired during learning can be applied to a broader context. Effectiveness of the method is demonstrated empirically.

URI

https://hdl.handle.net/11511/54510

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

FRACTAL SET-THEORETIC ANALYSIS OF PERFORMANCE LOSSES FOR TUNING TRAINING DATA IN LEARNING-SYSTEMS Erkmen, Aydan Müşerref (1992-08-28) This paper focuses on the evaluation of learning performance in intelligent dynamic processes with supervised learning. Learning dynamics are characterized by basins of attraction generated by state transitions in control space (statespace + parameter space). State uncertainty is modelled as a cellular control space, namely the cell space. Learning performance losses are related to nonseparable basins of attractions with fuzzy boundaries and to their erosions under parameter changes. Basins erosions are ana...
State-dependent impulsive Cohen-Grossberg neural networks with time-varying delays Sayli, Mustafa; YILMAZ, ENES (2016-01-01) In this paper, a more general class of state-dependent impulsive Cohen-Grossberg neural networks having variable coefficients with time-varying delays is addressed. By means of B-equivalence method, we reduce this state-dependent impulsive neural networks system to a fix time impulsive neural networks system. Sufficient conditions for existence and global exponential stability of the equilibrium point as well as periodic solution are obtained by employing a suitable Lyapunov function, the Banach fixed point...
Behavior Categorization Using Correlation Based Adaptive Resonance Theory YAVAŞ, mustafa; Alpaslan, Ferda Nur (2009-06-26) This paper presents a new method of categorizing robot behavior, which is based on a variation of Correlation Based Adaptive Resonance Theory (CobART) learning. CobART is a type of ART 2 network and its main contribution is the usage of correlation analysis methods for category matching. This study uses derivation based correspondence and Euclidian distance as correlation analysis methods for behavior categorization. Tests show that the proposed method generates better results than ART 2 categorization even...
Learning on the border: Active learning in imbalanced data classification Ertekin Bolelli, Şeyda; Bottou, Leon; Giles, C Lee (2007-10-06) This paper is concerned with the class imbalance problem which has been known to hinder the learning performance of classification algorithms. The problem occurs when there are significantly less number of observations of the target concept. Various real-world classification tasks, such as medical diagnosis, text categorization and fraud detection suffer from this phenomenon. The standard machine learning algorithms yield better prediction performance with balanced datasets. In this paper, we demonstrate th...
Cluster stability using minimal spanning trees Barzily, Zeev; Volkovich, Zeev; Akteke-Oeztuerk, Basak; Weber, Gerhard Wilhelm (2008-05-23) In this paper, a method for the study of cluster stability is purposed. We draw pairs of samples from the data, according to two sampling distributions. The first distribution corresponds to the high density zones of data-elements distribution. It is associated with the clusters cores. The second one, associated with the cluster margins, is related to the low density zones. The samples are clustered and the two obtained partitions are compared. The partitions are considered to be consistent if the obtained ...

Citation Formats

S. Girgin, F. Polat, and R. Alhajj, “State Similarity Based Approach for Improving Performance in RL,” 2007, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/54510.