{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MDWQUDGP5OQZQBJLNT2KEWIDVF","short_pith_number":"pith:MDWQUDGP","schema_version":"1.0","canonical_sha256":"60ed0a0ccfeba198052b6cf4a25903a97b3fb30135469be0b6f7c4cc44e25c2d","source":{"kind":"arxiv","id":"2211.11603","version":1},"attestation_state":"computed","paper":{"title":"Model-based Trajectory Stitching for Improved Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles A. Hepburn, Giovanni Montana","submitted_at":"2022-11-21T16:00:39Z","abstract_excerpt":"In many real-world applications, collecting large and high-quality datasets may be too costly or impractical. Offline reinforcement learning (RL) aims to infer an optimal decision-making policy from a fixed set of data. Getting the most information from historical data is then vital for good performance once the policy is deployed. We propose a model-based data augmentation strategy, Trajectory Stitching (TS), to improve the quality of sub-optimal historical trajectories. TS introduces unseen actions joining previously disconnected states: using a probabilistic notion of state reachability, it"},"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":"2211.11603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-21T16:00:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7c9c4f5e5ec7aead38aefd63683acc037504586eadb5f0eff6209fedf87537e0","abstract_canon_sha256":"8040d0e4544b2eff39cf47f13940157f07fd114fea74fb7d7a99a78403a9897d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:55.874846Z","signature_b64":"0PQD21iU4NyyASH5VuTlMMs0DDnwVcealA1Y75w1VOKWbLzYjnYZ2nXgG6lLk81DXvRagPDt9ooJ1oiSpHdfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60ed0a0ccfeba198052b6cf4a25903a97b3fb30135469be0b6f7c4cc44e25c2d","last_reissued_at":"2026-07-05T05:17:55.874348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:55.874348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-based Trajectory Stitching for Improved Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles A. Hepburn, Giovanni Montana","submitted_at":"2022-11-21T16:00:39Z","abstract_excerpt":"In many real-world applications, collecting large and high-quality datasets may be too costly or impractical. Offline reinforcement learning (RL) aims to infer an optimal decision-making policy from a fixed set of data. Getting the most information from historical data is then vital for good performance once the policy is deployed. We propose a model-based data augmentation strategy, Trajectory Stitching (TS), to improve the quality of sub-optimal historical trajectories. TS introduces unseen actions joining previously disconnected states: using a probabilistic notion of state reachability, it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11603","kind":"arxiv","version":1},"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/2211.11603/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":"2211.11603","created_at":"2026-07-05T05:17:55.874410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.11603v1","created_at":"2026-07-05T05:17:55.874410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11603","created_at":"2026-07-05T05:17:55.874410+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDWQUDGP5OQZ","created_at":"2026-07-05T05:17:55.874410+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDWQUDGP5OQZQBJL","created_at":"2026-07-05T05:17:55.874410+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDWQUDGP","created_at":"2026-07-05T05:17:55.874410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14350","citing_title":"Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03075","citing_title":"Refining Compositional Diffusion for Reliable Long-Horizon Planning","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDWQUDGP5OQZQBJLNT2KEWIDVF","json":"https://pith.science/pith/MDWQUDGP5OQZQBJLNT2KEWIDVF.json","graph_json":"https://pith.science/api/pith-number/MDWQUDGP5OQZQBJLNT2KEWIDVF/graph.json","events_json":"https://pith.science/api/pith-number/MDWQUDGP5OQZQBJLNT2KEWIDVF/events.json","paper":"https://pith.science/paper/MDWQUDGP"},"agent_actions":{"view_html":"https://pith.science/pith/MDWQUDGP5OQZQBJLNT2KEWIDVF","download_json":"https://pith.science/pith/MDWQUDGP5OQZQBJLNT2KEWIDVF.json","view_paper":"https://pith.science/paper/MDWQUDGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.11603&json=true","fetch_graph":"https://pith.science/api/pith-number/MDWQUDGP5OQZQBJLNT2KEWIDVF/graph.json","fetch_events":"https://pith.science/api/pith-number/MDWQUDGP5OQZQBJLNT2KEWIDVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDWQUDGP5OQZQBJLNT2KEWIDVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDWQUDGP5OQZQBJLNT2KEWIDVF/action/storage_attestation","attest_author":"https://pith.science/pith/MDWQUDGP5OQZQBJLNT2KEWIDVF/action/author_attestation","sign_citation":"https://pith.science/pith/MDWQUDGP5OQZQBJLNT2KEWIDVF/action/citation_signature","submit_replication":"https://pith.science/pith/MDWQUDGP5OQZQBJLNT2KEWIDVF/action/replication_record"}},"created_at":"2026-07-05T05:17:55.874410+00:00","updated_at":"2026-07-05T05:17:55.874410+00:00"}