Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning

@article{Eysenbach2017LeaveNT,
  title={Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning},
  author={Benjamin Eysenbach and Shixiang Gu and Julian Ibarz and Sergey Levine},
  journal={CoRR},
  year={2017},
  volume={abs/1711.06782}
}
Deep reinforcement learning algorithms can learn complex behavioral skills, but real-world application of these methods requires a large amount of experience to be collected by the agent. In practical settings, such as robotics, this involves repeatedly attempting a task, resetting the environment between each attempt. However, not all tasks are easily or automatically reversible. In practice, this learning process requires extensive human intervention. In this work, we propose an autonomous… CONTINUE READING