PDF 138998 - Hierar...pdf | Request a copy Full text restricted

Abstract

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 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 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: https://youtu.be/YQYQwLPXaL4

Item Type:	Conference or Workshop Item (Paper)
Authors/Creators:	Cao, Z and Wong, K and Bai, Q and Lin, C-T
Keywords:	unity, multi-agent interactions, hierarchical, reinforcement learning, agent
Journal or Publication Title:	Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2020)
Publisher:	International Foundation for Autonomous Agents and Multiagent Systems
Copyright Information:	Copyright 2020 International Foundation for AutonomousAgents and Multiagent Systems
Related URLs:	Google Scholar: Cao, Z
Item Statistics:	View statistics for this item

Actions (login required)

Item Control Page