Poster: Unraveling Reward Functions for Head-to-Head Autonomous Racing in AWS DeepRacer
Poster: Unraveling Reward Functions for Head-to-Head Autonomous Racing in AWS DeepRacer
复制标题
海报：揭开 AWS DeepRacer 中面对面自动赛车的奖励功能
DOI：
10.1145/3565287.3617987
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Yang, Kecheng
中科院分区：
文献类型：
--
作者：
Tian, Allen;John, Eddy Guerra;Yang, Kecheng
AWS DeepRacer是一款完全自主的1/18比例赛车，旨在帮助开发人员通过基于云的模拟和真实世界的赛车来学习和实践强化学习。驱动强化学习模型的是奖励函数，这是一种向代理提供积极或消极反馈的方式，通过分配数值来指导其在强化学习中的学习过程。在AWS培训环境中，有多种模式可供您运行培训模拟和评估。这些模式包括计时赛，物体回避和一个相对较新的模式：头到机器人。在这个项目中所做的研究主要集中在测试头对机器人模式中的奖励功能，以及开发一个适合这种新的头对机器人模式的研究功能。开发的算法优于默认的中心线奖励功能，以及对象回避奖励功能。
AWS DeepRacer is a fully autonomous 1/18th scale race car designed to help developers learn and practice reinforcement learning through cloud-based simulations and real-world racing. What drives the reinforcement learning model is the reward function, a way to provide positive or negative feedback to an agent, guiding its learning process in reinforcement learning by assigning numerical values. In the AWS training environment, there are multiple modes in which you can run training simulations and evaluations in. These modes include Time Trial, Object Avoidance, and a relatively new mode: Head to Bot. The research done in this project was primarily focused on testing reward functions in the Head to Bot mode as well as developing a research function that would be suited for training in this new Head to Bot mode. The developed algorithm outperformed the default Centerline reward function, as well as the Object Avoidance reward function.
AWS DeepRacer 上用于赛车和物体躲避的强化学习方法
DOI：
10.1109/compsac57700.2023.00129
发表时间：
2023
期刊：
Proceedings of the 47th IEEE Annual International Computer Software and Applications Conference (COMPSAC
影响因子：
--
作者：
McCalip, Jacob;Pradhan, Mandil;Yang, Kecheng
通讯作者：
Yang, Kecheng
DeepRacer自动驾驶平台中多车动态协同规划方法
DOI：
10.23919/ccc55666.2022.9902120
发表时间：
2022
期刊：
2022 41st Chinese Control Conference (CCC)
影响因子：
--
作者：
Haikuo Du;Moyan Zhu;Wenjie Zhu;Yanbo Liu;Anbei Zhao;Wenchao Xu;Weiqi Sun;Chunrun Du
通讯作者：
Chunrun Du