A Data-Efficient Deep Learning Approach for Deployable Multimodal Social Robots
arXiv:1908.10398 · doi:10.1016/j.neucom.2018.09.104
Abstract
The deep supervised and reinforcement learning paradigms (among others) have the potential to endow interactive multimodal social robots with the ability of acquiring skills autonomously. But it is still not very clear yet how they can be best deployed in real world applications. As a step in this direction, we propose a deep learning-based approach for efficiently training a humanoid robot to play multimodal games---and use the game of `Noughts & Crosses' with two variants as a case study. Its minimum requirements for learning to perceive and interact are based on a few hundred example images, a few example multimodal dialogues and physical demonstrations of robot manipulation, and automatic simulations. In addition, we propose novel algorithms for robust visual game tracking and for competitive policy learning with high winning rates, which substantially outperform DQN-based baselines. While an automatic evaluation shows evidence that the proposed approach can be easily extended to new games with competitive robot behaviours, a human evaluation with 130 humans playing with the Pepper robot confirms that highly accurate visual perception is required for successful game play.
References in corpus (9)
- Prioritized Experience Replay
- End-to-End Training of Deep Visuomotor Policies
- DRAW: A Recurrent Neural Network For Image Generation
- Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
- Massively Parallel Methods for Deep Reinforcement Learning
- Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening
- Show, Attend and Interact: Perceivable Human-Robot Social Interaction through Neural Attention Q-Network
- Training an Interactive Humanoid Robot Using Multimodal Deep Reinforcement Learning
- Deep Reinforcement Learning for Chatbots Using Clustered Actions and Human-Likeness Rewards