Towards optimized actions in critical situations of soccer games with deep reinforcement learning

Rahimian, Pegah; Oroojlooy, Afshin; Toka, László

doi:10.1109/dsaa53316.2021.9564207

Cited by 8 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, Dick and Brefeld 19 used RL to rate player positioning in soccer. It was in the works by Rahimian et al 20,21 that used RL to directly derive optimal policy rather than action valuation in soccer. In contrast to the latter two papers that aim to maximize the expected goals of the attacking teams, the current work assists both offensive and defensive players in terms of selecting the most impactful actions at the interrupting point of a possession.…”

Section: Related Workmentioning

confidence: 99%

A data-driven approach to assist offensive and defensive players in optimal decision making

Rahimian

Toka²

2023

International Journal of Sports Science & Coaching

Self Cite

View full text Add to dashboard Cite

Among all the popular sports, soccer is a relatively long-lasting game with a small number of goals per game. This renders the decision-making cumbersome, since it is not straightforward to evaluate the impact of in-game actions apart from goal scoring. Although several action valuation metrics and counterfactual reasoning have been proposed by researchers in recent years, assisting coaches in discovering the optimal actions in different situations of a soccer game has received little attention of soccer analytics. This work proposes the application of deep reinforcement learning on the event and tracking data of soccer matches to discover the most impactful actions at the interrupting point of a possession. Our optimization framework assists players and coaches in inspecting the optimal action, and on a higher level, we provide for the adjustment required for the teams in terms of their action frequencies in different pitch zones. The optimization results have different suggestions for offensive and defensive teams. For the offensive team, the optimal policy suggests more shots in half-spaces (i.e. long-distance shots). For the defending team, the optimal policy suggests that when locating in wings, defensive players should increase the frequency of fouls and ball outs rather than clearances, and when located in the centre, players should increase the frequency of clearances rather than fouls and ball outs.

show abstract

Section: Related Workmentioning

confidence: 99%

A data-driven approach to assist offensive and defensive players in optimal decision making

Rahimian

Toka²

2023

International Journal of Sports Science & Coaching

Self Cite

View full text Add to dashboard Cite

show abstract

“…The current methods using artificial intelligence could predict where a player will pass the ball (pass selection), 7 the likelihood of that pass being completed (pass success) 4,7 and whether this pass will result in a scoring opportunity (pass valuation). 9,10,12,5,6,8 It was in the work by Rahimian et al 13 that used RL to directly derive optimal policy rather than action valuation in soccer. Later on, they expanded the framework for finding the best action for both offensive and defensive phases of a soccer match.…”

Section: Related Workmentioning

confidence: 99%

Towards maximizing expected possession outcome in soccer

Rahimian

Haaren

Toka

2023

International Journal of Sports Science & Coaching

Self Cite

View full text Add to dashboard Cite

Soccer players need to make many decisions throughout a match in order to maximize their team’s chances of winning. Unfortunately, these decisions are challenging to measure and evaluate due to the low-scoring, complex, and highly dynamic nature of soccer. This article proposes an end-to-end deep reinforcement learning framework that receives raw tracking data for each situation in a game, and yields optimal ball destination location on the full surface of the pitch. Using the proposed approach, soccer players and coaches are able to analyze the actual behavior in their historical games, obtain the optimal behavior and plan for future games, and evaluate the outcome of the optimal decisions prior to deployment in a match. Concisely, the results of our optimization model propose more short passes (Tiki-Taka playing style) in all phases of a ball possession, and higher propensity of low distance shots (i.e. shots in attack phase). Such a modification will let the typical teams to increase their likelihood of possession ending in a goal by 0.025.

show abstract

“…From the RL perspective, numerous studies have focused on inverse approaches. To value on-ball actions, several studies have estimated Q-function or other policy functions [5], [6], [8], [17]. However, they often consider teams as a single agent and did not valuate off-ball players in all time steps (without events).…”

Section: Related Workmentioning

confidence: 99%

“…In these frameworks, it would be difficult to consider possible (i.e., counterfactual) actions as time goes back from a goal or other events. To value on-ball actions in terms of obtaining rewards (e.g., goals), there have been studies using reinforcement learning (RL) [5]- [8]. These works typically consider teams as a single agent and valuate an on-ball player or a team in irregularly occurring events (e.g., passes and shots).…”

Section: Introductionmentioning

confidence: 99%

Action Valuation of On- and Off-Ball Soccer Players Based on Multi-Agent Deep Reinforcement Learning

Nakahara,

Tsutsui,

Takeda

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Analysis of invasive sports such as soccer is challenging because the game situation changes continuously in time and space, and multiple agents individually recognize the game situation and make decisions. Previous studies using deep reinforcement learning have often considered teams as a single agent and valued the teams and players who hold the ball in each discrete event. Then it was challenging to value the actions of multiple players, including players far from the ball, in a spatiotemporally continuous state space. In this paper, we propose a method of valuing possible actions for on-and off-ball soccer players in a single holistic framework based on multi-agent deep reinforcement learning. We consider a discrete action space in each data frame that mimics that of Google research football and leverages supervised learning for actions in reinforcement learning. In the experiment, we analyzed the relationships with conventional indicators, season goals, and game ratings by experts, and showed the effectiveness of the proposed method. Our approach can assess how multiple players move continuously throughout the game, which is difficult to be discretized or labeled but vital for teamwork, scouting, and fan engagement.

show abstract

Towards optimized actions in critical situations of soccer games with deep reinforcement learning

Cited by 8 publications

References 8 publications

A data-driven approach to assist offensive and defensive players in optimal decision making

A data-driven approach to assist offensive and defensive players in optimal decision making

Towards maximizing expected possession outcome in soccer

Action Valuation of On- and Off-Ball Soccer Players Based on Multi-Agent Deep Reinforcement Learning

Contact Info

Product

Resources

About