{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WUFI6RGNWCI2FFOSTQLX3Q3FUQ","short_pith_number":"pith:WUFI6RGN","schema_version":"1.0","canonical_sha256":"b50a8f44cdb091a295d29c177dc365a41a17de48e5db24abd9cf04da3e0adf52","source":{"kind":"arxiv","id":"2211.11096","version":2},"attestation_state":"computed","paper":{"title":"Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Alexander Nikulin, Denis Tarasov, Dmitriy Akimov, Sergey Kolesnikov, Vladislav Kurenkov","submitted_at":"2022-11-20T21:57:10Z","abstract_excerpt":"Offline reinforcement learning aims to train a policy on a pre-recorded and fixed dataset without any additional environment interactions. There are two major challenges in this setting: (1) extrapolation error caused by approximating the value of state-action pairs not well-covered by the training data and (2) distributional shift between behavior and inference policies. One way to tackle these problems is to induce conservatism - i.e., keeping the learned policies closer to the behavioral ones. To achieve this, we build upon recent works on learning policies in latent action spaces and use a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2211.11096","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T21:57:10Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"3e8fc7cb2e7563b77950716b0db8894f07d6dc5a76131f89f09d8893b9da0f6d","abstract_canon_sha256":"e5a866dc08a70c806235fb676e2604cda70626f7ea5fe5eaf73414e932431cb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:51.209974Z","signature_b64":"zMJ9FppTrcTy7DN4SzXhevk1zDayWA22x7i9B1ROK3Wu8QRvu+x9U6QEUs20vX9mlBEyQmEN7SJd00DDFIMxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b50a8f44cdb091a295d29c177dc365a41a17de48e5db24abd9cf04da3e0adf52","last_reissued_at":"2026-07-05T05:36:51.209497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:51.209497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Alexander Nikulin, Denis Tarasov, Dmitriy Akimov, Sergey Kolesnikov, Vladislav Kurenkov","submitted_at":"2022-11-20T21:57:10Z","abstract_excerpt":"Offline reinforcement learning aims to train a policy on a pre-recorded and fixed dataset without any additional environment interactions. There are two major challenges in this setting: (1) extrapolation error caused by approximating the value of state-action pairs not well-covered by the training data and (2) distributional shift between behavior and inference policies. One way to tackle these problems is to induce conservatism - i.e., keeping the learned policies closer to the behavioral ones. To achieve this, we build upon recent works on learning policies in latent action spaces and use a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11096","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.11096/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.11096","created_at":"2026-07-05T05:36:51.209555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.11096v2","created_at":"2026-07-05T05:36:51.209555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11096","created_at":"2026-07-05T05:36:51.209555+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUFI6RGNWCI2","created_at":"2026-07-05T05:36:51.209555+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUFI6RGNWCI2FFOS","created_at":"2026-07-05T05:36:51.209555+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUFI6RGN","created_at":"2026-07-05T05:36:51.209555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08803","citing_title":"Some Essential Constructive Foundations for Systems and Control","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24405","citing_title":"Generative OOD-regularized Model-based Policy Optimization","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09580","citing_title":"SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WUFI6RGNWCI2FFOSTQLX3Q3FUQ","json":"https://pith.science/pith/WUFI6RGNWCI2FFOSTQLX3Q3FUQ.json","graph_json":"https://pith.science/api/pith-number/WUFI6RGNWCI2FFOSTQLX3Q3FUQ/graph.json","events_json":"https://pith.science/api/pith-number/WUFI6RGNWCI2FFOSTQLX3Q3FUQ/events.json","paper":"https://pith.science/paper/WUFI6RGN"},"agent_actions":{"view_html":"https://pith.science/pith/WUFI6RGNWCI2FFOSTQLX3Q3FUQ","download_json":"https://pith.science/pith/WUFI6RGNWCI2FFOSTQLX3Q3FUQ.json","view_paper":"https://pith.science/paper/WUFI6RGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.11096&json=true","fetch_graph":"https://pith.science/api/pith-number/WUFI6RGNWCI2FFOSTQLX3Q3FUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WUFI6RGNWCI2FFOSTQLX3Q3FUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUFI6RGNWCI2FFOSTQLX3Q3FUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUFI6RGNWCI2FFOSTQLX3Q3FUQ/action/storage_attestation","attest_author":"https://pith.science/pith/WUFI6RGNWCI2FFOSTQLX3Q3FUQ/action/author_attestation","sign_citation":"https://pith.science/pith/WUFI6RGNWCI2FFOSTQLX3Q3FUQ/action/citation_signature","submit_replication":"https://pith.science/pith/WUFI6RGNWCI2FFOSTQLX3Q3FUQ/action/replication_record"}},"created_at":"2026-07-05T05:36:51.209555+00:00","updated_at":"2026-07-05T05:36:51.209555+00:00"}