{"id":"doi:10.5555/2343576.2343644","kind":"article","title":"Reinforcement learning from simultaneous human and MDP reward","authors":["W. Bradley Knox","Peter Stone"],"author_count":2,"year":2012,"published":"2012-06-04","venue":null,"cited_by":162,"doi":"10.5555/2343576.2343644","arxiv_id":null,"nct_id":null,"source_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.1175","archive_url":"https://space-kitty.com/papers/doi:10.5555/2343576.2343644","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W2294422333","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":[]}