{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MX3EBN6Q6X7SDVLXSPOTLOWG7N","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"40421da55b08cd833c3b20a124d8656d99c81d1030cec07f4ea94d152218f9a0","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T09:34:31Z","title_canon_sha256":"c4825e837449d283fb1956fbb3f11d305ed4bbfdb7ada555c39f8365a6889f70"},"schema_version":"1.0","source":{"id":"2405.19878","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19878","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19878v1","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19878","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"pith_short_12","alias_value":"MX3EBN6Q6X7S","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"pith_short_16","alias_value":"MX3EBN6Q6X7SDVLX","created_at":"2026-07-05T08:25:13Z"},{"alias_kind":"pith_short_8","alias_value":"MX3EBN6Q","created_at":"2026-07-05T08:25:13Z"}],"graph_snapshots":[{"event_id":"sha256:c19052820bbcf475786db055fb094bad336e13f77d35587fdbaab6294a8479c6","target":"graph","created_at":"2026-07-05T08:25:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.19878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative models such as diffusion have been employed as world models in offline reinforcement learning to generate synthetic data for more effective learning. Existing work either generates diffusion models one-time prior to training or requires additional interaction data to update it. In this paper, we propose a novel approach for offline reinforcement learning with closed-loop policy evaluation and world-model adaptation. It iteratively leverages a guided diffusion world model to directly evaluate the offline target policy with actions drawn from it, and then performs an importance-sample","authors_text":"Tian Lan, Zeyu Fang","cross_cats":["cs.GT"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T09:34:31Z","title":"Learning from Random Demonstrations: Offline Reinforcement Learning with Importance-Sampled Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19878","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:45a6938a5c0cf75e69fc50491bb10b74cf359552f57291bf97f8d109ced052f7","target":"record","created_at":"2026-07-05T08:25:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"40421da55b08cd833c3b20a124d8656d99c81d1030cec07f4ea94d152218f9a0","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T09:34:31Z","title_canon_sha256":"c4825e837449d283fb1956fbb3f11d305ed4bbfdb7ada555c39f8365a6889f70"},"schema_version":"1.0","source":{"id":"2405.19878","kind":"arxiv","version":1}},"canonical_sha256":"65f640b7d0f5ff21d57793dd35bac6fb7c13974879ddae6e9b1611fc72739ee3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65f640b7d0f5ff21d57793dd35bac6fb7c13974879ddae6e9b1611fc72739ee3","first_computed_at":"2026-07-05T08:25:13.748730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:13.748730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lm+g08qx6lK9zOymvuJrmoJ0be6kvi1GqH9uHiMyCzzE2Y80xlisutQXPzfUjbvs6xn6jTXqFIl5aGZWv6MmCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:13.749153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19878","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45a6938a5c0cf75e69fc50491bb10b74cf359552f57291bf97f8d109ced052f7","sha256:c19052820bbcf475786db055fb094bad336e13f77d35587fdbaab6294a8479c6"],"state_sha256":"7dc0929937f48d8b2c20e495990b1bbfa24456492da0ce5db734973e708e7092"}