Role‐based attention in deep reinforcement learning for games
- 31 January 2021
- journal article
- research article
- Published by Wiley in Computer Animation and Virtual Worlds
- Vol. 32 (2) , e1978
Abstract
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.Keywords
Funding Information
- National Basic Research Program of China (2017YFB1300203)
This publication has 5 references indexed in Scilit:
- Attention-Based Curiosity-Driven Exploration in Deep Reinforcement Learning2020
- CBAM: Convolutional Block Attention Module2018
- Squeeze-and-Excitation Networks2018
- SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning2017
- Mastering the game of Go with deep neural networks and tree searchNature, 2016