홈 › Papers

Google Research Football: A Novel Reinforcement Learning Environment

2019-07-25 · Karol Kurach, Anton Raichuk, Piotr Stańczyk, Michał Zając, Olivier Bachem, Lasse Espeholt, Carlos Riquelme, Damien Vincent, Marcin Michalski, Olivier Bousquet, Sylvain Gelly

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.

📄 PDF Abstract BibTeX arXiv:1907.11180

Code (1)

google-research/football 공식 구현 tf

Tasks

Game of Footballreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Prioritized Experience Replay Prioritized Experience Replay is a type of experience replay in reinforcement learning where we more frequently replay…

Ape-X Ape-X is a distributed architecture for deep reinforcement learning. The algorithm decouples acting from learning: the actors interact with their own instances of the…

Entropy Regularization 설명 없음

PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…

Graph Neural Network based Agent in Google Research Football

2022-04-23 · Yizhan Niu, Jinglong Liu, Yuhao Shi, Jiren Zhu

Deep neural networks (DNN) can approximate value functions or policies for reinforcement learning, which makes the reinforcement learning algorithms more powerful. However, some DNNs, such as convolutional neural network…

Graph Neural Network Q-Learning reinforcement-learning Reinforcement Learning+1

Embedding Contextual Information through Reward Shaping in Multi-Agent Learning: A Case Study from Google Football

2023-03-25 · Chaoyi Gu, Varuna De Silva, Corentin Artaud, Rafael Pina

Artificial Intelligence has been used to help human complete difficult tasks in complicated environments by providing optimized strategies for decision-making or replacing the manual labour. In environments including mul…

Decision Making Imitation Learning Multi-agent Reinforcement Learning

TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play

2023-02-15 · Fanqi Lin, Shiyu Huang, Tim Pearce, Wenze Chen 외

Multi-agent football poses an unsolved challenge in AI research. Existing work has focused on tackling simplified scenarios of the game, or else leveraging expert demonstrations. In this paper, we develop a multi-agent s…

TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations

2021-10-09 · Shiyu Huang, Wenze Chen, Longfei Zhang, Shizhen Xu 외

Deep reinforcement learning (DRL) has achieved super-human performance on complex video games (e.g., StarCraft II and Dota II). However, current DRL systems still suffer from challenges of multi-agent coordination, spars…

Deep Reinforcement Learning Starcraft Starcraft II

An Empirical Study on Google Research Football Multi-agent Scenarios

2023-05-16 · Yan Song, He Jiang, Zheng Tian, Haifeng Zhang 외

Few multi-agent reinforcement learning (MARL) research on Google Research Football (GRF) focus on the 11v11 multi-agent full-game scenario and to the best of our knowledge, no open benchmark on this scenario has been rel…

Benchmarking Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning