SVD Reduction in Continuos Environment Reinforcement Learning
نویسنده
چکیده
Reinforcement learning methods, surviving the control difficulties of the unknown environment, are gaining more and more popularity recently in the autonomous robotics community. One of the possible difficulties of the reinforcement learning applications in complex situations is the huge size of the statevalueor action-value-function representation [2]. The case of continuous environment (continuous valued) reinforcement learning could be even complicated, as the state-valueor action-value-functions are turning into continuous functions. In this paper we suggest a way for tackling these difficulties by the application of SVD (Singular Value Decomposition) methods [3], [4], [15], [26].
منابع مشابه
A New Approach for the Solution of MultipleObjective Optimization Problems Based onReinforcement
Many problems can be characterized by several competing objectives. Multiple objective optimization problems have recently received considerable attention specially by the evolutionary algorithms community. Their proposals, however, require an adequate codiication of the problem into strings, which is not always easy to do. This paper introduces a new algorithm, called MDQL, for multiple object...
متن کاملA New Distributed Reinforcement Learning Algorithm for MultipleObjective Optimization
This paper describes a new algorithm, called MDQL, for the solution of multiple objective optimization problems. MDQL is based on a new distributed Q-learning algorithm, called DQL, which is also introduced in this paper. In DQL a family of independent agents, exploring diierent options, nds a common policy in a common environment. Information about action goodness is transmitted using traces o...
متن کاملMulticast Routing in Wireless Sensor Networks: A Distributed Reinforcement Learning Approach
Wireless Sensor Networks (WSNs) are consist of independent distributed sensors with storing, processing, sensing and communication capabilities to monitor physical or environmental conditions. There are number of challenges in WSNs because of limitation of battery power, communications, computation and storage space. In the recent years, computational intelligence approaches such as evolutionar...
متن کاملIntelligent Control of a Sensor-Actuator System via Kernelized Least-Squares Policy Iteration
In this paper a new framework, called Compressive Kernelized Reinforcement Learning (CKRL), for computing near-optimal policies in sequential decision making with uncertainty is proposed via incorporating the non-adaptive data-independent Random Projections and nonparametric Kernelized Least-squares Policy Iteration (KLSPI). Random Projections are a fast, non-adaptive dimensionality reduction f...
متن کاملLearning Overcomplete Representations from Distributed Data: A Brief Review
Most of the research on dictionary learning has focused on developing algorithms under the assumption that data is available at a centralized location. But often the data is not available at a centralized location due to practical constraints like data aggregation costs, privacy concerns, etc. Using centralized dictionary learning algorithms may not be the optimal choice in such settings. This ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2001