eCite Digital Repository

Hierarchical and non-hierarchical multi-agent interactions based on unity reinforcement learning


Cao, Z and Wong, K and Bai, Q and Lin, C-T, Hierarchical and non-hierarchical multi-agent interactions based on unity reinforcement learning, Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2020), 9-13 May2020, University of Auckland (virtual/online), pp. 2095-2097. (2020) [Refereed Conference Paper]

Restricted - Request a copy

Copyright Statement

Copyright 2020 International Foundation for Autonomous Agents and Multiagent Systems

Official URL:


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 multipleagent 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 agentís 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 nonhierarchical 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.

The demonstration video can be viewed at the following link:

Item Details

Item Type:Refereed Conference Paper
Keywords:unity, multi-agent interactions, hierarchical, reinforcement learning, agent
Research Division:Information and Computing Sciences
Research Group:Machine learning
Research Field:Neural networks
Objective Division:Defence
Objective Group:Defence
Objective Field:Intelligence, surveillance and space
UTAS Author:Cao, Z (Dr Zehong Cao)
UTAS Author:Wong, K (Mr Kai Chiu Wong)
UTAS Author:Bai, Q (Dr Quan Bai)
ID Code:138998
Year Published:2020
Deposited By:Information and Communication Technology
Deposited On:2020-05-18
Last Modified:2020-10-27
Downloads:4 View Download Statistics

Repository Staff Only: item control page