{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YQAGUQNGI32IZY6ZSTRRPLSAYL","short_pith_number":"pith:YQAGUQNG","schema_version":"1.0","canonical_sha256":"c4006a41a646f48ce3d994e317ae40c2c76896b046bbb3fbb54260f333c90300","source":{"kind":"arxiv","id":"2404.10393","version":2},"attestation_state":"computed","paper":{"title":"Offline Trajectory Optimization for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fajie Yuan, Jun Ma, Liu Yang, Pengjie Ren, Xin Xin, Yunsen Liang, Zhaochun Ren, Zhumin Chen, Ziqi Zhao","submitted_at":"2024-04-16T08:48:46Z","abstract_excerpt":"Offline reinforcement learning (RL) aims to learn policies without online explorations. To enlarge the training data, model-based offline RL learns a dynamics model which is utilized as a virtual environment to generate simulation data and enhance policy learning. However, existing data augmentation methods for offline RL suffer from (i) trivial improvement from short-horizon simulation; and (ii) the lack of evaluation and correction for generated data, leading to low-qualified augmentation.\n  In this paper, we propose offline trajectory optimization for offline reinforcement learning (OTTO). "},"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":"2404.10393","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T08:48:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a9a85d5868e4b7ebdd3135ef4500a51d3b94518d719efeb1c959c8748ce1a974","abstract_canon_sha256":"4c5e42644aacf2697e1535b32b9b94e2ff585d91483d44b0ce719499597587be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:41.817539Z","signature_b64":"gVyiAeyVvPILVUW+70WxvAYmTxV7fJuJCYNAU8rMDA3AK1w2rjV+M/TJeqDipQOzXXOHJIbUeAtYZYlFAe5/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4006a41a646f48ce3d994e317ae40c2c76896b046bbb3fbb54260f333c90300","last_reissued_at":"2026-07-05T11:34:41.817091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:41.817091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Trajectory Optimization for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fajie Yuan, Jun Ma, Liu Yang, Pengjie Ren, Xin Xin, Yunsen Liang, Zhaochun Ren, Zhumin Chen, Ziqi Zhao","submitted_at":"2024-04-16T08:48:46Z","abstract_excerpt":"Offline reinforcement learning (RL) aims to learn policies without online explorations. To enlarge the training data, model-based offline RL learns a dynamics model which is utilized as a virtual environment to generate simulation data and enhance policy learning. However, existing data augmentation methods for offline RL suffer from (i) trivial improvement from short-horizon simulation; and (ii) the lack of evaluation and correction for generated data, leading to low-qualified augmentation.\n  In this paper, we propose offline trajectory optimization for offline reinforcement learning (OTTO). "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10393","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/2404.10393/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":"2404.10393","created_at":"2026-07-05T11:34:41.817146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10393v2","created_at":"2026-07-05T11:34:41.817146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10393","created_at":"2026-07-05T11:34:41.817146+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQAGUQNGI32I","created_at":"2026-07-05T11:34:41.817146+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQAGUQNGI32IZY6Z","created_at":"2026-07-05T11:34:41.817146+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQAGUQNG","created_at":"2026-07-05T11:34:41.817146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00347","citing_title":"LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement Learning","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL","json":"https://pith.science/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL.json","graph_json":"https://pith.science/api/pith-number/YQAGUQNGI32IZY6ZSTRRPLSAYL/graph.json","events_json":"https://pith.science/api/pith-number/YQAGUQNGI32IZY6ZSTRRPLSAYL/events.json","paper":"https://pith.science/paper/YQAGUQNG"},"agent_actions":{"view_html":"https://pith.science/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL","download_json":"https://pith.science/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL.json","view_paper":"https://pith.science/paper/YQAGUQNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10393&json=true","fetch_graph":"https://pith.science/api/pith-number/YQAGUQNGI32IZY6ZSTRRPLSAYL/graph.json","fetch_events":"https://pith.science/api/pith-number/YQAGUQNGI32IZY6ZSTRRPLSAYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL/action/storage_attestation","attest_author":"https://pith.science/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL/action/author_attestation","sign_citation":"https://pith.science/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL/action/citation_signature","submit_replication":"https://pith.science/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL/action/replication_record"}},"created_at":"2026-07-05T11:34:41.817146+00:00","updated_at":"2026-07-05T11:34:41.817146+00:00"}