| Title: |
Hierarchical and non-hierarchical multi-agent interactions based on unity reinforcement learning |
| Authors: |
Cao, Z; Wong, K; Bai, Q; Lin, CT |
| Publication Year: |
2021 |
| Collection: |
University of Technology Sydney: OPUS - Open Publications of UTS Scholars |
| Description: |
© 2020 International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS). All rights reserved. The open-source Unity platform, where agents can be trained using hierarchical or non-hierarchical reinforcement learning, supports the use of games and simulations as environments for multiple-agent interactions. In this demonstration, we present hierarchical and non-hierarchical multi-agent interactions based on Unity reinforcement learning, specifically, hierarchical reinforcement learning that sets different levels of agent's observations to achieve the goal. We created four multi-agent scenarios in the Unity environment, namely, Crawler, Tennis, Banana Collector, and Soccer, to test the interaction performances of hierarchical and non-hierarchical reinforcement learning. The simulation-interaction performances show that hierarchical reinforcement learning can be applied to multi-agent environments and can compete with agents trained via non-hierarchical reinforcement learning. |
| Document Type: |
conference object |
| File Description: |
application/pdf |
| Language: |
English |
| ISBN: |
978-1-4503-7518-4; 1-4503-7518-9 |
| ISSN: |
1548-8403; 1558-2914 |
| Relation: |
Office of Naval ResearchGRANT12630695; Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS; Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, 2020, 2020-May, pp. 2095-2097; http://hdl.handle.net/10453/147184 |
| Availability: |
http://hdl.handle.net/10453/147184 |
| Rights: |
info:eu-repo/semantics/openAccess |
| Accession Number: |
edsbas.26F8A9F5 |
| Database: |
BASE |