{"work":{"id":"50cd3da1-adab-415b-ab3c-123ba918dbd4","openalex_id":"https://openalex.org/W3033324992","doi":"10.48550/arxiv.2006.04779","arxiv_id":"2006.04779","raw_key":null,"title":"spread\" of the distribution. Thediversity of orderqis defined as the generalized mean (of order1−q) of the inverse typicality (or “atypicality","authors":null,"authors_text":"Aviral Kumar, Aurick Zhou, George Tucker, and Sergey Levine","year":2020,"venue":"arXiv (Cornell University)","abstract":null,"external_url":"https://arxiv.org/abs/2006.04779","cited_by_count":537,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T05:45:22.590298+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Conservative Q-Learning for Offline Reinforcement Learning, August 2020","render_title":"Conservative Q-Learning for Offline Reinforcement Learning, August 2020"},"hub":{"state":{"work_id":"50cd3da1-adab-415b-ab3c-123ba918dbd4","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":18,"external_cited_by_count":537,"distinct_field_count":7,"first_pith_cited_at":"2021-08-06T20:48:30+00:00","last_pith_cited_at":"2026-07-02T12:30:50+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-23T18:09:51.298081+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":1},{"context_role":"baseline","n":1},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"baseline","n":1},{"context_polarity":"support","n":1},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}