Mixed Deep Reinforcement Learning-behavior Tree for Intelligent Agents Design

Lei Li, Lei Wang, Yuanzhi Li, Jie Sheng

2021

Abstract

Intelligent agent design has increasingly enjoyed the great advancements in real-world applications but most agents are also required to possess the capacities of learning and adapt to complicated environments. In this work, we investigate a general and extendable model of mixed behavior tree (MDRL-BT) upon the option framework where the hierarchical architecture simultaneously involves different deep reinforcement learning nodes and normal BT nodes. The emphasis of this improved model lies in the combination of neural network learning and restrictive behavior framework without conflicts. Moreover, the collaborative nature of two aspects can bring the benefits of expected intelligence, scalable behaviors and flexible strategies for agents. Afterwards, we enable the execution of the model and search for the general construction pattern by focusing on popular deep RL algorithms, PPO and SAC. Experimental performances in both Unity 2D and 3D environments demonstrate the feasibility and practicality of MDRL-BT by comparison with the-state-of-art models. Furthermore, we embed the curiosity mechanism into the MDRL-BT to facilitate the extensions.

Paper Citation

in Harvard Style

Li L., Wang L., Li Y. and Sheng J. (2021). Mixed Deep Reinforcement Learning-behavior Tree for Intelligent Agents Design.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-758-484-8, pages 113-124. DOI: 10.5220/0010316901130124

in Bibtex Style

@conference{icaart21,
author={Lei Li and Lei Wang and Yuanzhi Li and Jie Sheng},
title={Mixed Deep Reinforcement Learning-behavior Tree for Intelligent Agents Design},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2021},
pages={113-124},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010316901130124},
isbn={978-989-758-484-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - Mixed Deep Reinforcement Learning-behavior Tree for Intelligent Agents Design
SN - 978-989-758-484-8
AU - Li L.
AU - Wang L.
AU - Li Y.
AU - Sheng J.
PY - 2021
SP - 113
EP - 124
DO - 10.5220/0010316901130124