R
Ruofan Kong
Researcher at Microsoft
Publications - 12
Citations - 234
Ruofan Kong is an academic researcher from Microsoft. The author has contributed to research in topics: Mobile robot & Source code. The author has an hindex of 6, co-authored 12 publications receiving 196 citations. Previous affiliations of Ruofan Kong include Stevens Institute of Technology.
Papers
More filters
Journal ArticleDOI
Cooperative Distributed Source Seeking by Multiple Robots: Algorithms and Experiments
Shuai Li,Ruofan Kong,Yi Guo +2 more
TL;DR: This work considers the problem of source seeking using a group of mobile robots equipped with sensors for source concentration measurement, and presents two control algorithms with all-to-all and limited communications, respectively.
Posted Content
Deep Reinforcement Learning for Dexterous Manipulation with Concept Networks.
Aditya Gudimella,Ross Story,Matineh Shaker,Ruofan Kong,Matthew Brown,Victor Shnayder,Marcos M. Campos +6 more
TL;DR: This work introduces Concept Network Reinforcement Learning (CNRL), a framework which allows us to decompose problems using a multi-level hierarchy, and demonstrates the strength of CNRL by training a model to grasp a rectangular prism and precisely stack it on top of a cube using a gripper on a Kinova JACO arm.
Patent
Artificial intelligence engine having multiple independent processes on a cloud based platform configured to scale
Mark Isaac Hammond,Keen McEwan Browne,Shane Arney,Matthew E. Haigh,Jett Evan Jones,Matthew Brown,Ruofan Kong,Chetan Desh +7 more
TL;DR: In this article, multiple independent processes are configured as an independent process wrapped in its own container so that multiple instances of the same processes can run simultaneously to scale to handle one or more users to perform actions.
Patent
For hiearchical decomposition deep reinforcement learning for an artificial intelligence model
Marcos M. Campos,Aditya Gudimella,Ross Story,Martineh Shaker,Ruofan Kong,Matthew Brown,Victor Shnayder +6 more
TL;DR: In this article, the authors apply a hierarchical-decomposition reinforcement learning technique to train one or more AI objects as concept nodes composed in a hierarchical graph incorporated into an AI model.
Patent
Artificial Intelligence Engine Having Various Algorithms to Build Different Concepts Contained Within a Same AI Model
TL;DR: In this article, a learning topology representing a first concept can be built by the first module with a first dynamic programming training algorithm, while a learning space representing a second concept in the same model can be constructed by the second module with the first policy optimization algorithm.