An analysis of Reinforcement Learning applied to Coach task in IEEE Very Small Size Soccer

TL;DR

This paper explores the application of Reinforcement Learning to develop an adaptive coaching strategy in simulated robot soccer matches, demonstrating promising results against top teams.

Contribution

It introduces an end-to-end RL-based coaching system that learns optimal formations based on game conditions and opponent strategies in VSSS.

Findings

Achieved a win/loss ratio of approximately 2.0 against a top team.

Trained RL policies effectively against various opponent strategies.

Showed potential for RL in dynamic, multi-agent robotic sports environments.

Abstract

The IEEE Very Small Size Soccer (VSSS) is a robot soccer competition in which two teams of three small robots play against each other. Traditionally, a deterministic coach agent will choose the most suitable strategy and formation for each adversary's strategy. Therefore, the role of a coach is of great importance to the game. In this sense, this paper proposes an end-to-end approach for the coaching task based on Reinforcement Learning (RL). The proposed system processes the information during the simulated matches to learn an optimal policy that chooses the current formation, depending on the opponent and game conditions. We trained two RL policies against three different teams (balanced, offensive, and heavily offensive) in a simulated environment. Our results were assessed against one of the top teams of the VSSS league, showing promising results after achieving a win/loss ratio of approximately 2.0.