Maximizing BCI Human Feedback using Active Learning

  title={Maximizing BCI Human Feedback using Active Learning},
  author={Zi-zhao Wang and Junyao Shi and Iretiayo Akinola and P. Allen},
  journal={2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  • Zi-zhao Wang, Junyao Shi, +1 author P. Allen
  • Published 2020
  • Computer Science
  • 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • Recent advancements in Learning from Human Feedback present an effective way to train robot agents via inputs from non-expert humans, without a need for a specially designed reward function. However, this approach needs a human to be present and attentive during robot learning to provide evaluative feedback. In addition, the amount of feedback needed grows with the level of task difficulty and the quality of human feedback might decrease over time because of fatigue. To overcome these… CONTINUE READING

    Figures and Topics from this paper


    Accelerated Robot Learning via Human Brain Signals
    • 3
    • PDF
    Human in the Loop of Robot Learning: EEG-Based Reward Signal for Target Identification and Reaching Task
    • 6
    Reinforcement learning from simultaneous human and MDP reward
    • 130
    • PDF
    Deep Reinforcement Learning from Human Preferences
    • 352
    • Highly Influential
    • PDF
    Skill Learning by Autonomous Robotic Playing using Active Learning and Creativity
    • 16
    • PDF
    Training an Actor-Critic Reinforcement Learning Controller for Arm Movement Using Human-Generated Rewards
    • 20
    • PDF
    Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces
    • 84
    • PDF
    Policy Shaping: Integrating Human Feedback with Reinforcement Learning
    • 209
    • PDF
    Interactively shaping agents via human reinforcement: the TAMER framework
    • 304
    • Highly Influential
    • PDF