Md. Abdus Samad Kamal Efficient Reinforcement Learning in High Dimensional Domains


This book presents development of efficient reinforcement learning methods in a postgraduate research? Coordinated Multiagent Reinforcement Learning technique uses coordinator-agent hierarchy to keep the size of..! Three new methods are proposed to make the learning efficient according to the characteristics of the problems: Task-Oriented Reinforcement Learning reduces the problem size by viewing it from the tasks viewpoint that clarifies task relevant state variables. In large domains visiting every state-action pair is not feasible by an agent, therefore standard reinforcement learning approach is not applicable in solving many real world problems! Symmetrical-Actions Reinforcement Leaning reduces the size of a learning problem by exploiting partial symmetry over action relevant state variables and representing actions values by a single function. A reinforcement learning agent tries every state-action pair to find the optimal policy without prior knowledge about the domain.

Раззаков Ф.И. Непревзойденные

Hari Narain Srivastava Earthquake predictability, chaos and principal components analysis

Donald Wigal Pollock

Обновлено: 07.01.2017 в 17:23


Добавить комментарий

Ваш e-mail не будет опубликован. Обязательные поля помечены *

Asteroid Theme - Шаблоны сайтов - Форум WordPress