State Space Reduction for Hierarchical Policy Formation
نویسندگان
چکیده
model, then there should not exist a policy that leads from s′ to s in the original
منابع مشابه
Hierarchical Reinforcement Learning in Computer Games
Hierarchical reinforcement learning is an increasingly popular research field. In hierarchical reinforcement learning the complete learning task is decomposed into smaller subtasks that are combined in a hierarchical network. The subtasks can then be learned independently. A hierarchical decomposition can potentially facilitate state abstractions (i.e., bring forth a reduction in state space co...
متن کاملAction Dependent State Space Abstraction for Hierarchical Learning Systems
To operate effectively in complex environments learning agents have to selectively ignore irrelevant details by forming useful abstractions. In this paper we outline a formulation of abstraction for reinforcement learning approaches to stochastic decision problems by extending one of the recent minimization models, known as ǫ-reduction. The technique presented here extends ǫ-reduction to SMDPs ...
متن کاملAn Integral Method of Evaluating the Innovative Capacity of Enterprises
Innovative capacity as a potential ability of an enterprise to innovative development is manifested in the process of formation and realization of an innovative product, which can be embodied in various forms. In the article innovation capacity is considered as a complex concept that covers the innovative output of the enterprise and the reserve for providing innovative capacity, which can make...
متن کاملHierarchical Dialogue Policy Learning using Flexible State Transitions and Linear Function Approximation
Conversational agents that use reinforcement learning for policy optimization in large domains often face the problem of limited scalability. This problem can be addressed either by using function approximation techniques that estimate an approximate true value function, or by using a hierarchical decomposition of a learning task into subtasks. In this paper, we present a novel approach for dia...
متن کاملHierarchical 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 کامل