To achieve social interactions within Human-Robot Interaction (HRI) environments is a very challenging task. Most of the current research focuses on Wizard-of-Oz approaches, which neglect the recent development of intelligent robots. On the other hand, real-world scenarios usually do not provide the necessary control and reproducibility which are needed for learning algorithms. In this paper, we propose a virtual simulation environment that implements the Chef's Hat card game, designed to be used in HRI scenarios, to provide a controllable and reproducible scenario for reinforcement-learning algorithms.
A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning
University College London(伦敦大学学院);University of Edinburgh(爱丁堡大学);DeepMind(深度思维);Institute for AI, Peking University(北京大学人工智能研究院);Beijing Institute for General AI(北京通用人工智能研究院)
Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning
University of Oxford(牛津大学);Huawei R&D UK(华为英国研发中心);ShanghaiTech University(上海科技大学);Shanghai Jiao Tong University(上海交通大学);University College London(伦敦大学学院);Institute for AI, Peking University(北京大学人工智能研究院);BIGAI(北京通用人工智能研究院)
Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);Beijing Institute for General Artificial Intelligence(北京通用人工智能研究院);University of Oxford(牛津大学);University College London(伦敦大学学院);ReLER, AAII, University of Technology Sydney(悉尼科技大学AAII ReLER实验室)
Multi-Agent Reinforcement Learning for Heterogeneous Satellite Cluster Resources Optimization
STEM, University of South Australia(南澳大利亚大学STEM学院);School of Electrical Engineering, Computing and Mathematical Sciences (EECMS), Curtin University(Curtin大学电气工程、计算与数学科学学院);Systems Research Institute,Polish Academy of Sciences(波兰科学院系统研究所)