Trade-off on Sim2Real Learning: Real-world Learning Faster than Simulations
2022
会议录名称PROCEEDINGS 2022 8TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND ROBOTICS (ICCAR)
ISSN2251-2446
页码95-100
发表状态已发表
DOI10.1109/ICCAR55106.2022.9782656
摘要Deep Reinforcement Learning (DRL) experiments are commonly performed in simulated environments due to the tremendous training sample demands from deep neural networks. In contrast, model-based Bayesian Learning allows a robot to learn good policies within a few trials in the real world. Although it takes fewer iterations, Bayesian methods pay a relatively higher computational cost per trial, and the advantage of such methods is strongly tied to dimensionality and noise. In here, we compare a Deep Bayesian Learning algorithm with a model-free DRL algorithm while analyzing our results collected from both simulations and real-world experiments. While considering Sim and Real learning, our experiments show that the sample-efficient Deep Bayesian RL performance is better than DRL even when computation time (as opposed to number of iterations) is taken in consideration. Additionally, the difference in computation time between Deep Bayesian RL performed in simulation and in experiments point to a viable path to traverse the reality gap. We also show that a mix between Sim and Real does not outperform a purely Real approach, pointing to the possibility that reality can provide the best prior knowledge to a Bayesian Learning. Roboticists design and build robots every day, and our results show that a higher learning efficiency in the real-world will shorten the time between design and deployment by skipping simulations.
关键词deep reinforcement learning robotics decision making
会议名称INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND ROBOTICS (ICCAR)
会议地点Virtual, Online
会议日期April 8, 2022 - April 10, 2022
URL查看原文
收录类别EI
语种英语
EI入藏号/
来源库IEEE
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/183468
专题信息科学与技术学院
信息科学与技术学院_PI研究组_ANDRE LUIS MACEDO ROSENDO SILVA组
信息科学与技术学院_硕士生
作者单位
1.School of Information Science and Technology ShanghaiTech University, Shanghai, China
2.John A. Paulson School of Engineering and Applied Sciences Harvard University, Cambridge, Massachusetts, United States
第一作者单位信息科学与技术学院
第一作者的第一单位信息科学与技术学院
推荐引用方式
GB/T 7714
Jingyi Huang,Yizheng Zhang,Fabio Giardina,et al. Trade-off on Sim2Real Learning: Real-world Learning Faster than Simulations[C],2022:95-100.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Jingyi Huang]的文章
[Yizheng Zhang]的文章
[Fabio Giardina]的文章
百度学术
百度学术中相似的文章
[Jingyi Huang]的文章
[Yizheng Zhang]的文章
[Fabio Giardina]的文章
必应学术
必应学术中相似的文章
[Jingyi Huang]的文章
[Yizheng Zhang]的文章
[Fabio Giardina]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。