Corpus ID: 15399743

Training an Interactive Humanoid Robot Using Multimodal Deep Reinforcement Learning

  title={Training an Interactive Humanoid Robot Using Multimodal Deep Reinforcement Learning},
  author={Heriberto Cuay{\'a}huitl and Guillaume Couly and Cl{\'e}ment 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. We describe a learning approach as a step in this direction, where we teach a humanoid robot how to play the game of noughts and crosses. Given that multiple multimodal skills can be trained to play this game, we focus our attention to training the robot to perceive the game, and to… Expand
A Data-Efficient Deep Learning Approach for Deployable Multimodal Social Robots
An automatic evaluation shows evidence that the proposed approach can be easily extended to new games with competitive robot behaviours, and a human evaluation with 130 humans playing with the Pepper robot confirms that highly accurate visual perception is required for successful game play. Expand
Deep reinforcement learning for conversational robots playing games
  • H. Cuayáhuitl
  • Computer Science
  • 2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)
  • 2017
Experimental results show evidence that the proposed Deep Q-Networks method can lead to more effective policies than the baseline DQN method, which can be used for training interactive social robots. Expand
Robot Self-Assessment and Expression: A Learning Framework
A Robot Self-Assessment and Expression framework derived from reinforcement theory of motivation and the current state-of-the-art in machine learning is presented, theoretically describing how a robot could display emotional expressions depending on both predicted outcomes and actual outcomes of a task. Expand


Pragmatic Frames for Teaching and Learning in Human–Robot Interaction: Review and Challenges
The importance of pragmatic frames as flexible interaction protocols that provide important contextual cues to enable learners to infer new action or language skills and teachers to convey these cues are discussed. Expand
Human-level control through deep reinforcement learning
This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks. Expand
Strategic Dialogue Management via Deep Reinforcement Learning
A successful application of Deep Reinforcement Learning with a high-dimensional state space to the strategic board game of Settlers of Catan is described, which supports the claim that DRL is a promising framework for training dialogue systems, and strategic agents with negotiation abilities. Expand
Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control
This paper introduces a machine learning based system for controlling a robotic manipulator with visual perception only. The capability to autonomously learn robot controllers solely from raw-pixelExpand
End-to-End Training of Deep Visuomotor Policies
This paper develops a method that can be used to learn policies that map raw image observations directly to torques at the robot's motors, trained using a partially observed guided policy search method, with supervision provided by a simple trajectory-centric reinforcement learning method. Expand
Hierarchical reinforcement learning for situated natural language generation
A novel approach for situated Natural Language Generation in dialogue that is based on hierarchical reinforcement learning and learns the best utterance for a context by optimisation through trial and error is presented. Expand
Robot learning from verbal interaction: A brief survey
This brief survey points out the need of bringing robots out of the lab, into uncontrolled conditions, in order to investigate their usability and acceptance by end users. Expand
Reinforcement learning in robotics: A survey
This article attempts to strengthen the links between the two research communities by providing a survey of work in reinforcement learning for behavior generation in robots by highlighting both key challenges in robot reinforcement learning as well as notable successes. Expand
Temporal Difference Learning for the Game Tic-Tac-Toe 3D: Applying Structure to Neural Networks
The results on Tic-Tac-Toe 3D show that the deep structured neural network with integrated pattern detectors has the strongest performance out of the compared multilayer perceptrons against a fixed opponent, both through self-training and through training against this fixed opponent. Expand
Playing Atari with Deep Reinforcement Learning
This work presents the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning, which outperforms all previous approaches on six of the games and surpasses a human expert on three of them. Expand