Open AccessCuMARL: Curiosity-Based Learning in Multiagent Reinforcement Learning
Author(s) -
Devarani Devi Ningombam,
Byunghyun Yoo,
Hyun Woo Kim,
Hwa Jeon Song,
Sungwon Yi
Publication year - 2022
Publication title -
ieee access
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.587
H-Index - 127
ISSN - 2169-3536
DOI - 10.1109/access.2022.3198981
Subject(s) - aerospace , bioengineering , communication, networking and broadcast technologies , components, circuits, devices and systems , computing and processing , engineered materials, dielectrics and plasmas , engineering profession , fields, waves and electromagnetics , general topics for engineers , geoscience , nuclear engineering , photonics and electrooptics , power, energy and industry applications , robotics and control systems , signal processing and analysis , transportation
In this paper, we propose a novel curiosity-based learning algorithm for Multi-agent Reinforcement Learning (MARL) to attain efficient and effective decision-making. We employ the centralized training with decentralized execution framework (CTDE) and consider that each agent has knowledge of the prior action distribution of others. To quantify the difference in agents’ knowledge, curiosity, we introduce conditional mutual information (CMI) regularization and use the amount of information for updating decision-making policy. Then, to deploy these learning frameworks in a large-scale MARL setting while acquiring high sample efficiency, we consider a Kullback-Leibler (KL) divergence-based prioritization of experiences. We evaluate the effectiveness of the proposed algorithm in three different levels of StarCraft Multi Agent Challenge (SMAC) scenarios using the PyMARL framework. The simulation-based performance analysis shows that the proposed technique significantly improves the test win rate compared to various state-of-the-art MARL benchmarks, such as the Optimistically Weighted Monotonic Value Function Factorization (OW_QMIX) and Learning Individual Intrinsic Reward (LIIR).