Two-stage training algorithm for AI robot soccer

by   Taeyoung Kim, et al.

In multi-agent reinforcement learning, the cooperative learning behavior of agents is very important. In the field of heterogeneous multi-agent reinforcement learning, cooperative behavior among different types of agents in a group is pursued. Learning a joint-action set during centralized training is an attractive way to obtain such cooperative behavior, however, this method brings limited learning performance with heterogeneous agents. To improve the learning performance of heterogeneous agents during centralized training, two-stage heterogeneous centralized training which allows the training of multiple roles of heterogeneous agents is proposed. During training, two training processes are conducted in a series. One of the two stages is to attempt training each agent according to its role, aiming at the maximization of individual role rewards. The other is for training the agents as a whole to make them learn cooperative behaviors while attempting to maximize shared collective rewards, e.g., team rewards. Because these two training processes are conducted in a series in every timestep, agents can learn how to maximize role rewards and team rewards simultaneously. The proposed method is applied to 5 versus 5 AI robot soccer for validation. Simulation results show that the proposed method can train the robots of the robot soccer team effectively, achieving higher role rewards and higher team rewards as compared to other approaches that can be used to solve problems of training cooperative multi-agent.


page 1

page 4

page 5

page 7


Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward

Many cooperative multi-agent problems require agents to learn individual...

Value-Decomposition Networks For Cooperative Multi-Agent Learning

We study the problem of cooperative multi-agent reinforcement learning w...

A Dataset Schema for Cooperative Learning from Demonstration in Multi-robots Systems

Multi-Agent Systems (MASs) have been used to solve complex problems that...

Balancing Selection Pressures, Multiple Objectives, and Neural Modularity to Coevolve Cooperative Agent Behavior

Previous research using evolutionary computation in Multi-Agent Systems ...

Discovering Causality for Efficient Cooperation in Multi-Agent Environments

In cooperative Multi-Agent Reinforcement Learning (MARL) agents are requ...

Emergent Coordination Through Competition

We study the emergence of cooperative behaviors in reinforcement learnin...

Learning cooperative behaviours in adversarial multi-agent systems

This work extends an existing virtual multi-agent platform called RoboSu...

Please sign up or login with your details

Forgot password? Click here to reset