Training an Interactive Humanoid Robot Using Multimodal Deep Reinforcement Learning

1 code implementation • 26 Nov 2016 • Heriberto Cuayáhuitl, Guillaume Couly, Clément Olalainty

Training robots to perceive, act and communicate using multiple modalities still represents a challenging problem, particularly if robots are expected to learn efficiently from small sets of example interactions.

reinforcement-learning Reinforcement Learning (RL)