2016 International Conference on Autonomous Robot Systems and Competitions (ICARSC)最新文献_第6页

Multimodal Interaction and Serious Game for Assistive Robotic Devices in a Simulated Environment 模拟环境下辅助机器人设备的多模态交互与严肃博弈

2016 International Conference on Autonomous Robot Systems and Competitions (ICARSC) Pub Date : 2016-05-01 DOI: 10.1109/ICARSC.2016.54

B. Faria, Daniel Dias, Luis Paulo Reis, A. Moreira

引用次数: 1

User Centered Design of an Autonomous Mobile Robot Vending Machine Concept 以用户为中心的自主移动机器人自动售货机概念设计

2016 International Conference on Autonomous Robot Systems and Competitions (ICARSC) Pub Date : 2016-05-01 DOI: 10.1109/ICARSC.2016.67

Andre S. P. H. Navarro, C. Cardeira, C. Monteiro

引用次数: 5

Fast Computational Processing for Mobile Robots' Self-Localization 移动机器人自定位的快速计算处理

2016 International Conference on Autonomous Robot Systems and Competitions (ICARSC) Pub Date : 2016-05-01 DOI: 10.1109/ICARSC.2016.40

Helder Ribeiro, Pedro Silva, Ricardo Roriz, Tiago Maia, Rui Saraiva, G. Lopes, A. Ribeiro

引用次数: 0

Contextual Relative Entropy Policy Search with Covariance Matrix Adaptation 基于协方差矩阵自适应的上下文相对熵策略搜索

2016 International Conference on Autonomous Robot Systems and Competitions (ICARSC) Pub Date : 2016-05-01 DOI: 10.1109/ICARSC.2016.31

A. Abdolmaleki, D. Simões, N. Lau, Luis Paulo Reis, G. Neumann

{"title":"Contextual Relative Entropy Policy Search with Covariance Matrix Adaptation","authors":"A. Abdolmaleki, D. Simões, N. Lau, Luis Paulo Reis, G. Neumann","doi":"10.1109/ICARSC.2016.31","DOIUrl":"https://doi.org/10.1109/ICARSC.2016.31","url":null,"abstract":"Stochastic search algorithms are black-box optimizers of an objective function. They have recently gained a lot of attention in operations research, machine learning and policy search of robot motor skills due to their ease of use and their generality. However, with slightly different tasks or objective functions, many stochastic search algorithms require complete re-learning in order to adapt the solution to the new objective function or the new context. As such, we consider the contextual stochastic search paradigm. Here, we want to find good parameter vectors for multiple related tasks, where each task is described by a continuous context vector. Hence, the objective function might change slightly for each parameter vector evaluation. Contextual algorithms have been investigated in the field of policy search. However, contextual policy search algorithms typically suffer from premature convergence and perform unfavourably in comparison with state of the art stochastic search methods. In this paper, we investigate a contextual stochastic search algorithm known as Contextual Relative Entropy Policy Search (CREPS), an informationtheoretic algorithm that can learn for multiple tasks simultaneously. We extend that algorithm with a covariance matrix adaptation technique that alleviates the premature convergence problem. We call the new algorithm Contextual Relative Entropy Policy Search with Covariance Matrix Adaptation (CREPS-CMA). We will show that CREPS-CMA outperforms the original CREPS by orders of magnitude. We illustrate the performance of CREPS-CMA on several contextual tasks, including a complex simulated robot kick task.","PeriodicalId":260641,"journal":{"name":"2016 International Conference on Autonomous Robot Systems and Competitions (ICARSC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128516857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 10