Hierarchical Reinforcement Learning Applied
نویسندگان
چکیده
A general methodology for performance improvement of Intelligent Machines based on Hierarchical Reinforcement Learning is introduced. Machine Decision Making and Learning are based on a cost function which balances reliability and computational cost of algorithms at the three levels of the hierarchy proposed by Saridis. Despite this particular framework, the methodology intends to be suuciently general to encompass diierent types of architectures and applications. Novel contributions of this work include the deenition of a cost function combining reliability and complexity, recursively improved through feedback, a Hierarchical Reinforcement Learning and Decision Making algorithm which uses that cost function, and a coherent joint deenition of algorithm cost and reliability. Results of simulations show the application of the formalism to an Intelligent Robotic System mounted on an Autonomous Underwater Vehicle.
منابع مشابه
Hierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents
This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...
متن کاملHierarchical Reinforcement Learning on the Virtual Battlefield
This paper investigates the potential of flat and hierarchical reinforcement learning (HRL) for solving problems within strategy games. A HRL method, Max-Q, is applied to a unit transportation task modelled within a simplified, discrete real-time strategy game engine, and its performance compared to that of flat Q-learning. It is shown that reinforcement learning approaches, and especially hier...
متن کاملHierarchical Reinforcement Learning with Deictic Representation in a Computer Game
Computer games are challenging test beds for machine learning research. Without applying abstraction and generalization techniques, many traditional machine learning techniques, such as reinforcement learning, will fail to learn efficiently. In this paper we examine extensions of reinforcement learning that scale to the complexity of computer games. In particular we look at hierarchical reinfor...
متن کاملSignals Reinforcement Inputs Sensory Actions Skill Skill Skill
While the need for hierarchies within control systems is apparent, it is also clear to many researchers that such hierarchies should be learned. Learning both the structure and the component behaviors is a diicult task. The beneet of learning the hierarchical structures of behaviors is that the decomposition of the control structure into smaller transportable chunks allows previously learned kn...
متن کاملAutonomous Navigation in Partially Observable Environments Using Hierarchical Q-Learning
A self-learning adaptive flight control design allows reliable and effective operation of flight vehicles in a complex environment. Reinforcement Learning provides a model-free, adaptive, and effective process for optimal control and navigation. This paper presents a new and systematic approach combining Q-learning and hierarchical reinforcement learning with additional connecting Q-value funct...
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 2006