{"id":"openalex:W2098441518","kind":"article","title":"Policy Shaping: Integrating Human Feedback with Reinforcement Learning","authors":["Shane Griffith","K.A. Subramanian","Jonathan Scholz","Charles Lee Isbell","Andrea L. Thomaz"],"author_count":5,"year":2013,"published":"2013-12-05","venue":null,"cited_by":307,"doi":null,"arxiv_id":null,"nct_id":null,"source_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.646.510","archive_url":"https://space-kitty.com/papers/openalex:W2098441518","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W2098441518","pdf_url":null,"abstract":null,"abstract_license":null,"license":null,"is_open_access":false,"retracted":false,"peer_reviewed":null,"categories":["Reinforcement Learning in Robotics"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0).","topics":[{"slug":"alignment-safety","name":"AI Alignment & Safety","domain_slug":"ai"}],"cited_in_dossiers":[]}