How does AI play football? An analysis of RL and real-world football strategies
This work provides insights for sports analysts and RL researchers by comparing simulated and real-world football strategies, though it is incremental in applying existing methods to a new domain.
The paper analyzed the play-style characteristics of football reinforcement learning (RL) agents, finding strong correlations between agent competitiveness and social network analysis metrics, and that aspects of RL agents' play styles become similar to real-world footballers as agents become more competitive.
Recent advances in reinforcement learning (RL) have made it possible to develop sophisticated agents that excel in a wide range of applications. Simulations using such agents can provide valuable information in scenarios that are difficult to scientifically experiment in the real world. In this paper, we examine the play-style characteristics of football RL agents and uncover how strategies may develop during training. The learnt strategies are then compared with those of real football players. We explore what can be learnt from the use of simulated environments by using aggregated statistics and social network analysis (SNA). As a result, we found that (1) there are strong correlations between the competitiveness of an agent and various SNA metrics and (2) aspects of the RL agents play style become similar to real world footballers as the agent becomes more competitive. We discuss further advances that may be necessary to improve our understanding necessary to fully utilise RL for the analysis of football.