Google Research Football: A Novel Reinforcement Learning Environment

Abstract

Recent progress in the field of reinforcement learning has been accelerated by virtual learning environments such as video games, where novel algorithms and ideas can be quickly tested in a safe and reproducible manner. We introduce the Google Research Football Environment, a new reinforcement learning environment where agents are trained to play football in an advanced, physics-based 3D simulator. The resulting environment is challenging, easy to use and customize, and it is available under a permissive open-source license. In addition, it provides support for multiplayer and multi-agent experiments. We propose three full-game scenarios of varying difficulty with the Football Benchmarks and report baseline results for three commonly used reinforcement algorithms (IMPALA, PPO, and Ape-X DQN). We also provide a diverse set of simpler scenarios with the Football Academy and showcase several promising research directions.

The Combination of Artificial Intelligence and Extended Reality: A Systematic Review

“…Recently, AI agents have been used to play games such as Starcraft II, Dota 2, the ancient game of Go, and the iconic Atari console games (Kurach et al, 2020). The main objective for developing this application is to provide challenging environments to allow newly developed AI algorithms to be quickly trained and tested.…”

“…Another challenge is the lack of complexity in learning environments. A lack of real-world semantic complexity in a learning environment can cause the AI to be trained insufficiently to run in the real world (Kurach et al, 2020). Many learning environments offer simplified modes of interaction, a narrow set of tasks, and small-scale scenes.…”

Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning

“…The reward is +1 when scoring a goal, and −1 when conceding one to the opposing team. We refer the readers to (Kurach et al 2019) for the details.…”

Playtesting in Match 3 Game Using Strategic Plays via Reinforcement Learning

“…Researchers have endeavoured to create an agent capable of playing games in various genres. Artificial intelligence has demonstrated shown the ability to outplay humans by using deep learning and reinforcement learning, such as in Go, chess, shogi [11], [12], FPSs [13], [14], strategic simulation games [15], [16], racing games [17], card games [18], arcade games [19], [20], casual games [21]- [24] and sports games [25].…”