@inproceedings{policyshapingintegratinghumanfeedback,
  title = {Policy Shaping: Integrating Human Feedback with Reinforcement Learning},
  author = {Shane Griffith and Kaushik Subramanian and Jonathan Scholz and Charles L. Isbell and Andrea L. Thomaz},
  year = {2013},
  booktitle = {NeurIPS 2013 12},
  url = {http://papers.nips.cc/paper/5187-policy-shaping-integrating-human-feedback-with-reinforcement-learning},
}