eduzhai > Applied Sciences > Engineering >

Concept and the implementation of a tool to convert industry 40 environments modeled as FSM to an OpenAI Gym wrapper

  • Save

... pages left unread,continue reading

Document pages: 16 pages

Abstract: Industry 4.0 systems have a high demand for optimization in their tasks,whether to minimize cost, maximize production, or even synchronize theiractuators to finish or speed up the manufacture of a product. Those challengesmake industrial environments a suitable scenario to apply all modernreinforcement learning (RL) concepts. The main difficulty, however, is the lackof that industrial environments. In this way, this work presents the conceptand the implementation of a tool that allows us to convert any dynamic systemmodeled as an FSM to the open-source Gym wrapper. After that, it is possible toemploy any RL methods to optimize any desired task. In the first tests of theproposed tool, we show traditional Q-learning and Deep Q-learning methodsrunning over two simple environments.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...