Graph Neural Network Based Agent In Google Research Football

Abstract

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 networks (CNN), cannot extract enough information or take too long to obtain enough features from the inputs under specific circumstances of reinforcement learning. For example, the input data of Google Research Football, a reinforcement learning environment which trains agents to play football, is the small map of players' locations. The information is contained not only in the coordinates of players, but also in the relationships between different players. CNNs can neither extract enough information nor take too long to train. To address this issue, this paper proposes a deep q-learning network (DQN) with a graph neural network (GNN) as its model. The GNN transforms the input data into a graph which better represents the football players' locations so that it extracts more i

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyniu2022graph

Related papers

• Google Research Football: A Novel Reinforcement Learning Environment (2019)17.22
• Boosting Studies Of Multi-agent Reinforcement Learning On Google Research Football Environment: The Past, Present, And Future (2023)4.52
• Transformer Based Reinforcement Learning For Games (2019)0.00
• QGNN: Value Function Factorisation With Graph Neural Networks (2022)0.00
• Tikick: Towards Playing Multi-agent Football Full Games From Single-agent Demonstrations (2021)0.00
• An Empirical Study On Google Research Football Multi-agent Scenarios (2023)6.77
• Natural Gradient Deep Q-learning (2018)0.00
• Soft Q Network (2019)0.00