{"id":"doi:10.5555/1838206.1838208","kind":"article","title":"Combining manual feedback with subsequent MDP reward signals for reinforcement learning","authors":["W. Bradley Knox","Peter Stone"],"author_count":2,"year":2010,"published":"2010-05-10","venue":null,"cited_by":182,"doi":"10.5555/1838206.1838208","arxiv_id":null,"nct_id":null,"source_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.153.8692","archive_url":"https://space-kitty.com/papers/doi:10.5555/1838206.1838208","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W2116157560","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":[]}