{"id":"doi:10.1016/j.artint.2015.03.009","kind":"article","title":"Framing reinforcement learning from human reward: Reward positivity, temporal discounting, episodicity, and performance","authors":["W. Bradley Knox","Peter Stone"],"author_count":2,"year":2015,"published":"2015-04-06","venue":"Artificial Intelligence","cited_by":64,"doi":"10.1016/j.artint.2015.03.009","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1016/j.artint.2015.03.009","archive_url":"https://space-kitty.com/papers/doi:10.1016/j.artint.2015.03.009","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W1453801241","pdf_url":"https://www.sciencedirect.com/science/article/pii/S0004370215000557/pdf","abstract":null,"abstract_license":null,"license":null,"is_open_access":true,"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":[]}