Premium
Role‐based attention in deep reinforcement learning for games
Author(s) -
Yang Dong,
Yang Wenjing,
Li Minglong,
Yang Qiong
Publication year - 2021
Publication title -
computer animation and virtual worlds
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.225
H-Index - 49
eISSN - 1546-427X
pISSN - 1546-4261
DOI - 10.1002/cav.1978
Subject(s) - reinforcement learning , computer science , task (project management) , forcing (mathematics) , focus (optics) , function (biology) , artificial intelligence , football , convolutional neural network , bellman equation , human–computer interaction , machine learning , physics , management , climatology , evolutionary biology , law , political science , optics , economics , biology , geology , mathematics , mathematical economics
Reinforcement learning method that learns while interacting with the environment, relies heavily on the concept of state as the input to the policy and value function. In the task, the view of agent contains a lot of information, and it is difficult for the agent to learn to ignore the irrelevant information and focus on the key information. Inspired by recent work in attention models for computer vision, we present a role‐based attention model for reinforcement learning. The proposed model uses convolutional neural networks to generate soft attention maps, adding crucial role information in the task, forcing the agent to focus on important features and distinguish task‐related information. To validate the performance in complex problems, the proposed approach is evaluated in a challenging scenario, Football Academy in Google Research Football Environment , a newly released reinforcement learning environment with physics‐based three‐dimensional simulator. The experimental results demonstrate that agents using role‐based attention mechanism can perform better in football games.