Analysis of a Reinforcement Learning algorithm using Self-Organizing Maps
نویسندگان
چکیده
Abstract. The scenario of this work is defined by the need of many Machine Learning algorithms to tune a number of parameters that define its behavior; the resulting performance can be evaluated with different indices. The relationship between parameters and performance may be neither linear nor straightforward. This work proposes a qualitative approach to the afore-mentioned relationship by using Self-Organizing Maps due to their visual information processing. The approach is evaluated in the framework of Reinforcement Learning algorithms.
منابع مشابه
Visual Reinforcement Learning Algorithm using Self Organizing Maps and Its Simulation in OpenGL Environment
Recently, the camera systems becomes more available for mobile robots . But scene analysis for generating control signals is still difficult and consumes large computational power. For this problem, the control method which generates the control signals directly from the raw camera images will be effective. In this paper, we use the reinforcement learning using the camera image as input data. F...
متن کاملCombination of Reinforcement Learning and Dynamic Self Organizing Map for Robot Arm Control
This paper shows that a system with two link arm can obtain arm reaching movement to a target object by combination of reinforcement learning and dynamic self organizing map. Proposed model in this paper present state and action space of reinforcement learning with dynamis self organizing maps. Because these spaces are continuous. proposed model uses two dynamic self-organizing maps (DSOM) to e...
متن کاملNGTSOM: A Novel Data Clustering Algorithm Based on Game Theoretic and Self- Organizing Map
Identifying clusters is an important aspect of data analysis. This paper proposes a noveldata clustering algorithm to increase the clustering accuracy. A novel game theoretic self-organizingmap (NGTSOM ) and neural gas (NG) are used in combination with Competitive Hebbian Learning(CHL) to improve the quality of the map and provide a better vector quantization (VQ) for clusteringdata. Different ...
متن کاملThe Self Organization of Context for Learning in Multiagent Games
Reinforcement learning is an effective machine learning paradigm in domains represented by compact and discrete state-action spaces. In highdimensional and continuous domains, tile coding with linear function approximation has been widely used to circumvent the curse of dimensionality, but it suffers from the drawback that human-guided identification of features is required to create effective ...
متن کاملCombining Self-organizing Maps with Mixtures of Experts: Application to an Actor-Critic Model of Reinforcement Learning in the Basal Ganglia
In a reward-seeking task performed in a continuous environment, our previous work compared several Actor-Critic (AC) architectures implementing dopamine-like reinforcement learning mechanisms in the rat’s basal ganglia. The task complexity imposes the coordination of several AC submodules, each module being an expert trained in a particular subset of the task. We showed that the classical metho...
متن کامل