Accelerated Robot Learning via Human Brain Signals

@article{Akinola2020AcceleratedRL,
  title={Accelerated Robot Learning via Human Brain Signals},
  author={Iretiayo Akinola and Zizhao Wang and Junyao Shi and Xiaomin He and Pawan Lapborisuth and Jingxi Xu and David Watkins-Valls and P. Sajda and P. Allen},
  journal={2020 IEEE International Conference on Robotics and Automation (ICRA)},
  year={2020},
  pages={3799-3805}
}
  • Iretiayo Akinola, Zizhao Wang, +6 authors P. Allen
  • Published 2020
  • Computer Science
  • 2020 IEEE International Conference on Robotics and Automation (ICRA)
  • In reinforcement learning (RL), sparse rewards are a natural way to specify the task to be learned. However, most RL algorithms struggle to learn in this setting since the learning signal is mostly zeros. In contrast, humans are good at assessing and predicting the future consequences of actions and can serve as good reward/policy shapers to accelerate the robot learning process. Previous works have shown that the human brain generates an error-related signal, measurable using… CONTINUE READING
    3 Citations

    Figures from this paper

    Maximizing BCI Human Feedback using Active Learning
    • PDF
    Learning with Humans in the Loop
    • PDF

    References

    SHOWING 1-10 OF 34 REFERENCES
    Robot reinforcement learning using EEG-based reward signals
    • 52
    • PDF
    Shared control of a robot using EEG-based feedback signals
    • 7
    • PDF
    Human in the Loop of Robot Learning: EEG-Based Reward Signal for Target Identification and Reaching Task
    • 6
    Deep Reinforcement Learning from Human Preferences
    • 353
    • PDF
    Overcoming Exploration in Reinforcement Learning with Demonstrations
    • 265
    • PDF
    Correcting robot mistakes in real time using EEG signals
    • 81
    • PDF
    Brain Responses During Robot-Error Observation
    • 6
    • PDF
    Robot Learning From Demonstration
    • 659
    • PDF
    Training an Actor-Critic Reinforcement Learning Controller for Arm Movement Using Human-Generated Rewards
    • 20
    • PDF