Home // ICAS 2019, The Fifteenth International Conference on Autonomic and Autonomous Systems // View article

Deep Learning with Evolutionary Strategies for Building Autonomus Agents Beahviour

Authors:
Ventseslav Shopov
Vanya Markova

Keywords: Autonomous Agents; Reinforcement Learning; Evolutionary Strategies.

Abstract:
In this study, we will consider the construction of the behaviour of an autonomous agent in an environment that has many traps and a large number of obstacles. Such environments require the agent to build a policy that will lead them to the goal as quickly as possible. As a working basis, we use Reinforcement Learning and apply approaches from the field of random search and Evolutionary Strategies.

Pages: 55 to 58

Copyright: Copyright (c) IARIA, 2019

Publication date: June 2, 2019

Published in: conference

ISSN: 2308-3913

ISBN: 978-1-61208-712-2

Location: Athens, Greece

Dates: from June 2, 2019 to June 6, 2019