{"type":"ScholarlyArticle","title":"Policy Shaping with Human Teachers","authors":[{"name":"Thomas Cederborg","slug":"thomas-cederborg","given":"Thomas","family":"Cederborg","affiliation":""},{"name":"Ishaan Grover","slug":"ishaan-grover","given":"Ishaan","family":"Grover","affiliation":""},{"name":"Charles Lee Isbell Jr.","slug":"charles-lee-isbell-jr","given":"Charles Lee Isbell","family":"Jr.","affiliation":""},{"name":"Andrea Lockerd Thomaz","slug":"andrea-lockerd-thomaz","given":"Andrea Lockerd","family":"Thomaz","affiliation":""}],"abstract":"In this work we evaluate the performance of a policy shaping algorithm using 26 human teachers. We examine if the algorithm is suitable for human-generated data on two different boards in a pac-man domain, comparing performance to an oracle that provides critique based on one known winning policy. Perhaps surprisingly, we show that the data generated by our 26 participants yields even better performance for the agent than data generated by the oracle. This might be because humans do not discourage exploring multiple winning policies. Additionally, we evaluate the impact of different verbal instructions, and different interpretations of silence, finding that the usefulness of data is affected both by what instructions is given to teachers, and how the data is interpreted.","doi":null,"url":"https://ijcai.org/proceedings/2015/474","pdf":"https://ijcai.org/proceedings/2015/0474.pdf","markdown":"https://ijcai.org/proceedings/2015/474.md","bibtex":"https://ijcai.org/proceedings/2015/bibtex/474","volume":{"slug":"2015","title":"Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2015","url":"https://ijcai.org/proceedings/2015/","year":2015,"location":"Buenos Aires, Argentina","dates":"25–31 July 2015","editors":"Qiang Yang and Michael Wooldridge","isbn":"978-1-57735-738-4","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Special Track on Machine Learning","track":"Special Track on Machine Learning","number":474,"pages":{"first":3366,"last":3371},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}