Natural Language-Based Human–Machine Collaborative Learning Games Algorithm Based on Deep Rein-Forcement Learning
Human-machine collaborative game agents are usually in an open environment, and they typically obtain behavioral information through environmental rewards. However, traditional agent environment exploration techniques are limited in reward-sparse environments. Deep rein-forcement learning was adopte...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10433481/ |
_version_ | 1797292020410089472 |
---|---|
author | Le Na |
author_facet | Le Na |
author_sort | Le Na |
collection | DOAJ |
description | Human-machine collaborative game agents are usually in an open environment, and they typically obtain behavioral information through environmental rewards. However, traditional agent environment exploration techniques are limited in reward-sparse environments. Deep rein-forcement learning was adopted to design an algorithm with adversarial sparse reward environment rewards and improve the exploration ability and the decision-making ability of agents in electronic game environments. First, a human-machine collaboration model was designed using natural language instructions to guide the rein-forcement learning process of agents based on the concept of reward construction. Then, a hind-sight experience re-play algorithm was introduced to optimize it, solving the reward problem of human-machine collaborative agents in a sparse reward environment. These experiments confirmed that the designed natural language reward construction model could achieve a score of 9.8 in the game and achieve 92% prediction accuracy. The model optimized through hind-sight experience re-play could achieve a maximum accuracy of 97.8% in achieving target instructions and ultimately obtain a game score of 9.9. As a result, the designed natural language human-machine collaboration model has good application performance in coefficient reward environment games and can obtain better scores. |
first_indexed | 2024-03-07T19:46:11Z |
format | Article |
id | doaj.art-32265dd0373d486f8d34a6bfec4b88da |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-07T19:46:11Z |
publishDate | 2024-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-32265dd0373d486f8d34a6bfec4b88da2024-02-29T00:00:42ZengIEEEIEEE Access2169-35362024-01-0112288182883010.1109/ACCESS.2024.336550010433481Natural Language-Based Human–Machine Collaborative Learning Games Algorithm Based on Deep Rein-Forcement LearningLe Na0https://orcid.org/0009-0002-9407-415XSchool of Education, Jilin International Studies University, Jilin, Changchun, ChinaHuman-machine collaborative game agents are usually in an open environment, and they typically obtain behavioral information through environmental rewards. However, traditional agent environment exploration techniques are limited in reward-sparse environments. Deep rein-forcement learning was adopted to design an algorithm with adversarial sparse reward environment rewards and improve the exploration ability and the decision-making ability of agents in electronic game environments. First, a human-machine collaboration model was designed using natural language instructions to guide the rein-forcement learning process of agents based on the concept of reward construction. Then, a hind-sight experience re-play algorithm was introduced to optimize it, solving the reward problem of human-machine collaborative agents in a sparse reward environment. These experiments confirmed that the designed natural language reward construction model could achieve a score of 9.8 in the game and achieve 92% prediction accuracy. The model optimized through hind-sight experience re-play could achieve a maximum accuracy of 97.8% in achieving target instructions and ultimately obtain a game score of 9.9. As a result, the designed natural language human-machine collaboration model has good application performance in coefficient reward environment games and can obtain better scores.https://ieeexplore.ieee.org/document/10433481/Deep rein-forcement learningnatural language instructionsreward structurehind-sight experience re-playhuman-machine collaborationlearning games |
spellingShingle | Le Na Natural Language-Based Human–Machine Collaborative Learning Games Algorithm Based on Deep Rein-Forcement Learning IEEE Access Deep rein-forcement learning natural language instructions reward structure hind-sight experience re-play human-machine collaboration learning games |
title | Natural Language-Based Human–Machine Collaborative Learning Games Algorithm Based on Deep Rein-Forcement Learning |
title_full | Natural Language-Based Human–Machine Collaborative Learning Games Algorithm Based on Deep Rein-Forcement Learning |
title_fullStr | Natural Language-Based Human–Machine Collaborative Learning Games Algorithm Based on Deep Rein-Forcement Learning |
title_full_unstemmed | Natural Language-Based Human–Machine Collaborative Learning Games Algorithm Based on Deep Rein-Forcement Learning |
title_short | Natural Language-Based Human–Machine Collaborative Learning Games Algorithm Based on Deep Rein-Forcement Learning |
title_sort | natural language based human x2013 machine collaborative learning games algorithm based on deep rein forcement learning |
topic | Deep rein-forcement learning natural language instructions reward structure hind-sight experience re-play human-machine collaboration learning games |
url | https://ieeexplore.ieee.org/document/10433481/ |
work_keys_str_mv | AT lena naturallanguagebasedhumanx2013machinecollaborativelearninggamesalgorithmbasedondeepreinforcementlearning |