Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

A Data-efficiency Training Framework for Deep Reinforcement Learning

Version 1 : Received: 30 September 2022 / Approved: 30 September 2022 / Online: 30 September 2022 (10:35:06 CEST)

How to cite: Feng, W.; Han, C.; Lian, F.; Liu, X. A Data-efficiency Training Framework for Deep Reinforcement Learning. Preprints 2022, 2022090483. https://doi.org/10.20944/preprints202209.0483.v1 Feng, W.; Han, C.; Lian, F.; Liu, X. A Data-efficiency Training Framework for Deep Reinforcement Learning. Preprints 2022, 2022090483. https://doi.org/10.20944/preprints202209.0483.v1

Abstract

Sparse reward long horizon task is a major challenge for deep reinforcement learning algorithm. One of the key barriers is data-inefficiency. Even in the simulation environment, it usually takes weeks to training the agent. In this study, a data-efficiency training framework is proposed, where a curriculum learning is design for the agent in the simulation scenario. Different distributions of the initial state are set for the agent to get more informative reward during the whole training process. A fine-tuning of the parameters in the output layer of the neural network for value function is conduct to bridge the gap between sim-to-real. An experiment of UAV maneuver control is conducted in the proposed training framework to verify the method more efficient. We demonstrate that data-efficiency is different for the same data in different training stages.

Keywords

deep reinforcement learning; data efficient; curriculum learning; transfer learning

Subject

Engineering, Control and Systems Engineering

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.