Deep Reinforcement Learning of Abstract Reasoning from Demonstrations
暂无分享，去创建一个
We designed a Deep Q-Network (DQN) that learns to perform high-level reasoning in a Learning from Demonstration (LfD) domain involving the analysis of human responses. We test our system by having a NAO humanoid robot automatically deliver a behavioral intervention designed to teach social skills to individuals with Autism Spectrum Disorder (ASD). Our model extracts relevant features from the multi-modal input of tele-operated demonstrations in order to deliver the intervention correctly to novel participants.
[1] Günther Palm,et al. High-level learning from demonstration with conceptual spaces and subspace clustering , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).
[2] Shane Legg,et al. Human-level control through deep reinforcement learning , 2015, Nature.
[3] Manuel Lopes,et al. Active Learning for Teaching a Robot Grounded Relational Symbols , 2013, IJCAI.