Positive impact of state similarity on reinforcement learning performance

2007-10-01
Girgin, Sertan
Polat, Faruk
Alhaj, Reda
In this paper, we propose a novel approach to identify states with similar subpolicies and show how they can be integrated into the reinforcement learning framework to improve learning performance. The method utilizes a specialized tree structure to identify common action sequences of states, which are derived from possible optimal policies, and defines a similarity function between two states based on the number of such sequences. Using this similarity function, updates on the action-value function of a state are reflected onto all similar states. This allows experience that is acquired during learning to be applied to a broader context. The effectiveness of the method is demonstrated empirically.
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS

Suggestions

Free gait generation with reinforcement learning for a six-legged robot
Erden, Mustafa Suphi; Leblebicioğlu, Mehmet Kemal (Elsevier BV, 2008-03-31)
In this paper the problem of free gait generation and adaptability with reinforcement learning are addressed for a six-legged robot. Using the developed free gait generation algorithm the robot maintains to generate stable gaits according to the commanded velocity. The reinforcement learning scheme incorporated into the free gait generation makes the robot choose more stable states and develop a continuous walking pattern with a larger average stability margin. While walking in normal conditions with no ext...
Verification of Modular Diagnosability With Local Specifications for Discrete-Event Systems
Schmidt, Klaus Verner (Institute of Electrical and Electronics Engineers (IEEE), 2013-09-01)
In this paper, we study the diagnosability verification for modular discrete-event systems (DESs), i.e., DESs that are composed of multiple components. We focus on a particular modular architecture, where each fault in the system must be uniquely identified by the modular component where it occurs and solely based on event observations of that component. Hence, all diagnostic computations for faults to be detected in this architecture can be performed locally on the respective modular component, and the obt...
Experimental Validation of a Feed-Forward Predictor for the Spring-Loaded Inverted Pendulum Template
Uyanik, Ismail; Morgul, Omer; Saranlı, Uluç (Institute of Electrical and Electronics Engineers (IEEE), 2015-02-01)
Widely accepted utility of simple spring-mass models for running behaviors as descriptive tools, as well as literal control targets, motivates accurate analytical approximations to their dynamics. Despite the availability of a number of such analytical predictors in the literature, their validation has mostly been done in simulation, and it is yet unclear how well they perform when applied to physical platforms. In this paper, we extend on one of the most recent approximations in the literature to ensure it...
Multiagent reinforcement learning using function approximation
Abul, O; Polat, Faruk; Alhajj, R (Institute of Electrical and Electronics Engineers (IEEE), 2000-11-01)
Learning in a partially observable and nonstationary environment is still one of the challenging problems In the area of multiagent (MA) learning. Reinforcement learning is a generic method that suits the needs of MA learning in many aspects. This paper presents two new multiagent based domain independent coordination mechanisms for reinforcement learning; multiple agents do not require explicit communication among themselves to learn coordinated behavior. The first coordination mechanism Is perceptual coor...
A pattern classification approach for boosting with genetic algorithms
Yalabık, Ismet; Yarman Vural, Fatoş Tunay; Üçoluk, Göktürk; Şehitoğlu, Onur Tolga (2007-11-09)
Ensemble learning is a multiple-classifier machine learning approach which produces collections and ensembles statistical classifiers to build up more accurate classifier than the individual classifiers. Bagging, boosting and voting methods are the basic examples of ensemble learning. In this study, a novel boosting technique targeting to solve partial problems of AdaBoost, a well-known boosting algorithm, is proposed. The proposed system finds an elegant way of boosting a bunch of classifiers successively ...
Citation Formats
S. Girgin, F. Polat, and R. Alhaj, “Positive impact of state similarity on reinforcement learning performance,” IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, pp. 1256–1270, 2007, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/46977.