Next Article in Journal
Role-Engineering Optimization with Cardinality Constraints and User-Oriented Mutually Exclusive Constraints
Previous Article in Journal
Approximate Completed Trace Equivalence of ILAHSs Based on SAS Solving
Open AccessArticle

Fuzzy Reinforcement Learning and Curriculum Transfer Learning for Micromanagement in Multi-Robot Confrontation

by Chunyang Hu 1 and Meng Xu 2,*
1
School of Computer Engineering, Hubei University of Arts and Science, Xiangyang 441053, China
2
School of Computer Science, Northwestern Polytechnical University, Xi’an 710072, China
*
Author to whom correspondence should be addressed.
Information 2019, 10(11), 341; https://doi.org/10.3390/info10110341
Received: 12 October 2019 / Accepted: 30 October 2019 / Published: 2 November 2019
Multi-Robot Confrontation on physics-based simulators is a complex and time-consuming task, but simulators are required to evaluate the performance of the advanced algorithms. Recently, a few advanced algorithms have been able to produce considerably complex levels in the context of the robot confrontation system when the agents are facing multiple opponents. Meanwhile, the current confrontation decision-making system suffers from difficulties in optimization and generalization. In this paper, a fuzzy reinforcement learning (RL) and the curriculum transfer learning are applied to the micromanagement for robot confrontation system. Firstly, an improved Qlearning in the semi-Markov decision-making process is designed to train the agent and an efficient RL model is defined to avoid the curse of dimensionality. Secondly, a multi-agent RL algorithm with parameter sharing is proposed to train the agents. We use a neural network with adaptive momentum acceleration as a function approximator to estimate the state-action function. Then, a method of fuzzy logic is used to regulate the learning rate of RL. Thirdly, a curriculum transfer learning method is used to extend the RL model to more difficult scenarios, which ensures the generalization of the decision-making system. The experimental results show that the proposed method is effective.
Keywords: multi-robot confrontation; fuzzy reinforcement learning; curriculum transfer learning; neural network multi-robot confrontation; fuzzy reinforcement learning; curriculum transfer learning; neural network
MDPI and ACS Style

Hu, C.; Xu, M. Fuzzy Reinforcement Learning and Curriculum Transfer Learning for Micromanagement in Multi-Robot Confrontation. Information 2019, 10, 341.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop