Centralized Critic per Knowledge for Cooperative Multi-Agent Game Environments

Cooperative multiplayer games are based on rules where players must collaborate to solve certain tasks. These games bring specific challenges when using Multi-Agent Reinforcement Learning (MARL), since they present requirements related to the training of these collaborative behaviors, such as partia...

Full description

Saved in:
Bibliographic Details
Main Authors: Ferreira, Thais, Clua, Esteban, Kohwalter, Troy Costa
Format: Conference Proceeding
Language:English
Subjects:
Collaboration
Cooperative Multi-Agents
Entertainment industry
Games
MA-POCA
ML-Agents
Reinforcement learning
Task analysis
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Cooperative multiplayer games are based on rules where players must collaborate to solve certain tasks. These games bring specific challenges when using Multi-Agent Reinforcement Learning (MARL), since they present requirements related to the training of these collaborative behaviors, such as partial observations, non-stationary, and the problem of credit assignment. One of the approaches used in MARL to solve these challenges is centralized training with decentralized execution. The idea is to use the available knowledge about the full state and information of the environment in the training phase, but policy learning takes place in a decentralized way, not depending on this knowledge. In this work, we study the approach of centralized training with decentralized execution. We seek to validate whether the division of knowledge about the environment (e.g. observations, perception of objects, enemies, obstacles) by different groups (different centralized critics) improves learning performance in multi-agent environments. Our results show that specifying a centralized critic per knowledge improves the training, but it also increases the time of the training process.
ISSN:2159-6662
DOI:10.1109/SBGames54170.2021.00015