Corpus ID: 16498378

Simultaneous Control and Human Feedback in the Training of a Robotic Agent with Actor-Critic Reinforcement Learning

@article{Mathewson2016SimultaneousCA,
  title={Simultaneous Control and Human Feedback in the Training of a Robotic Agent with Actor-Critic Reinforcement Learning},
  author={K. Mathewson and P. Pilarski},
  journal={ArXiv},
  year={2016},
  volume={abs/1606.06979}
}
This paper contributes a preliminary report on the advantages and disadvantages of incorporating simultaneous human control and feedback signals in the training of a reinforcement learning robotic agent. While robotic human-machine interfaces have become increasingly complex in both form and function, control remains challenging for users. This has resulted in an increasing gap between user control approaches and the number of robotic motors which can be controlled. One way to address this gap… Expand
15 Citations
Actor-Critic Reinforcement Learning with Simultaneous Human Control and Feedback
  • 7
  • PDF
Reinforcement Learning based Embodied Agents Modelling Human Users Through Interaction and Multi-Sensory Perception
  • 3
  • PDF
Learning from demonstration: Teaching a myoelectric prosthesis with an intact limb via reinforcement learning
  • Gautham Vasan, P. Pilarski
  • Engineering, Computer Science
  • 2017 International Conference on Rehabilitation Robotics (ICORR)
  • 2017
  • 17
  • PDF
Training an Actor-Critic Reinforcement Learning Controller for Arm Movement Using Human-Generated Rewards
  • 23
  • Highly Influenced
  • PDF
Computational reinforcement learning using rewards from human feedback
  • PDF
Interactively shaping robot behaviour with unlabeled human instructions
  • 6
  • Highly Influenced
  • PDF
Learning User Preferences via Reinforcement Learning with Spatial Interface Valuing
  • PDF
Communicative Capital for Prosthetic Agents
  • 5
  • PDF
Reinforcement learning with human advice. A survey
  • 3
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 50 REFERENCES
Real-time prediction learning for the simultaneous actuation of multiple prosthetic joints
  • 36
  • PDF
Learning via human feedback in continuous state and action spaces
  • 26
Online human training of a myoelectric prosthesis controller via actor-critic reinforcement learning
  • 133
  • PDF
Teachable robots: Understanding human teaching behavior to build more effective robot learners
  • 330
  • PDF
Model-Free reinforcement learning with continuous action in practice
  • 133
  • PDF
Application of real-time machine learning to myoelectric prosthesis control: A case series in adaptive switching
  • 39
  • PDF
Neural network learning control of robot manipulators using gradually increasing task difficulty
  • T. Sanger
  • Computer Science
  • IEEE Trans. Robotics Autom.
  • 1994
  • 92
Biological arm motion through reinforcement learning
  • 52
  • PDF
...
1
2
3
4
5
...