본문 바로가기
  • Home

Cooperative Multi-agent Reinforcement Learning on Sparse Reward Battlefield Environment using QMIX and RND in Ray RLlib

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2024, 29(1), pp.11-19
  • DOI : 10.9708/jksci.2024.29.01.011
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : November 23, 2023
  • Accepted : December 28, 2023
  • Published : January 31, 2024

Minkyoung Kim 1

1한화시스템

Accredited

ABSTRACT

Multi-agent systems can be utilized in various real-world cooperative environments such as battlefield engagements and unmanned transport vehicles. In the context of battlefield engagements, where dense reward design faces challenges due to limited domain knowledge, it is crucial to consider situations that are learned through explicit sparse rewards. This paper explores the collaborative potential among allied agents in a battlefield scenario. Utilizing the Multi-Robot Warehouse Environment(RWARE) as a sparse reward environment, we define analogous problems and establish evaluation criteria. Constructing a learning environment with the QMIX algorithm from the reinforcement learning library Ray RLlib, we enhance the Agent Network of QMIX and integrate Random Network Distillation(RND). This enables the extraction of patterns and temporal features from partial observations of agents, confirming the potential for improving the acquisition of sparse reward experiences through intrinsic rewards.

Citation status

* References for papers published after 2022 are currently being built.