Abstract
Uncertainty and partial or unknown information about environment dynamics have led reward-based methods to play a key role in the Single-Agent and Multi-Agent Learning problem. Tree-based planning approaches such as Monte Carlo Tree Search algorithm have been a striking success in single-agent domains where a perfect simulator model is available, e.g., Go and chess strategic board games. This paper presents a decentralized tree-based planning scheme, that combines forward planning with direct reinforcement learning temporal-difference updates applied to the multi-agent setting. Forward planning requires an engine model which is learned from experience and represented via function approximation. Evaluation and validation are carried out in the Hunter-Prey Pursuit cooperative environment and performance is compared with state-of-the-art RL techniques. N-Step Dynamic Tree Search (NSDTS) pretends to adapt the most successful single-agent learning methods to the multi-agent boundaries in a decentralized system structure, dealing with scalability issues and exponential growth of computational resources suffered by centralized systems. NSDTS demonstrates to be a remarkable advance compared to the conventional Q-Learning temporal-difference method.
Original language | English |
---|---|
Title of host publication | AIAA SciTech Forum 2022 |
Publisher | American Institute of Aeronautics and Astronautics Inc, AIAA |
ISBN (Print) | 9781624106316 |
DOIs | |
Publication status | Published - 2022 |
Externally published | Yes |
Event | AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2022 - San Diego, United States Duration: 3 Jan 2022 → 7 Jan 2022 |
Publication series
Name | AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2022 |
---|
Conference
Conference | AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2022 |
---|---|
Country/Territory | United States |
City | San Diego |
Period | 3/01/22 → 7/01/22 |
Bibliographical note
Publisher Copyright:© 2022, American Institute of Aeronautics and Astronautics Inc.. All rights reserved.