Q-value Path Decomposition for Deep Multiagent Reinforcement Learning

By Yaodong Yang, Jianye Hao, Guangyong Chen, Hongyao Tang, Yingfeng Chen, Yujing Hu, Changjie Fan, Zhongyu Wei. 2020

65 citations recorded by the source corpus.

Recently, deep multiagent reinforcement learning (MARL) has become a highly active research area as many real-world problems can be inherently viewed as multiagent systems. A particularly interesting and widely applicable class of problems is the partially observable cooperative multiagent setting, in which a team of agents learns to coordinate their behaviors conditioning on their private observations and commonly shared global reward signals. One natural solution is to resort to the centralized training and decentralized execution paradigm. During centralized training, one key challenge is the multiagent credit assignment: how to allocate the global rewards for individual agent policies for better coordination towards maximizing system-level's benefits. In this paper, we propose a new method called Q-value Path Decomposition (QPD) to decompose the system's global Q-values into individual agents' Q-values. Unlike previous works which restrict the representation relation of the individual Q-values and the global one, we leverage the integrated gradient attribution technique into deep MARL to directly decompose global Q-values along trajectory paths to assign credits for agents. We evaluate QPD on the challenging StarCraft II micromanagement tasks and show that QPD achieves the state-of-the-art performance in both homogeneous and heterogeneous multiagent scenarios compared with existing cooperative MARL algorithms.

Subfields: Artificial Intelligence, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chenghao Li
2. Yiqin Yang
3. Xiaoteng Ma
4. Qianchuan Zhao

In Control and Systems Engineering

1. Chenghao Li
2. Yiqin Yang
3. Xiaoteng Ma
4. Qianchuan Zhao

Citations in the corpus

• Modeling the Interaction between Agents in Cooperative Multi-Agent Reinforcement Learning (2021, methodology): “In the CTDE framework, value-based methods receive the most attention and they can be divided into two categories: centralized value function methods and value decomposition methods [38].”