{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YFVVINSV5OVPG27PV6ROTUG2EL","short_pith_number":"pith:YFVVINSV","schema_version":"1.0","canonical_sha256":"c16b543655ebaaf36befafa2e9d0da22d016c6ec6cfe7e0b0bb05f5cec3ddb75","source":{"kind":"arxiv","id":"2310.20587","version":5},"attestation_state":"computed","paper":{"title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huazhe Xu, Ruizhe Shi, Simon S. Du, Yanjie Ze, Yuyao Liu","submitted_at":"2023-10-31T16:24:17Z","abstract_excerpt":"Offline reinforcement learning (RL) aims to find a near-optimal policy using pre-collected datasets. In real-world scenarios, data collection could be costly and risky; therefore, offline RL becomes particularly challenging when the in-domain data is limited. Given recent advances in Large Language Models (LLMs) and their few-shot learning prowess, this paper introduces $\\textbf{La}$nguage Models for $\\textbf{Mo}$tion Control ($\\textbf{LaMo}$), a general framework based on Decision Transformers to effectively use pre-trained Language Models (LMs) for offline RL. Our framework highlights four c"},"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":"2310.20587","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-31T16:24:17Z","cross_cats_sorted":[],"title_canon_sha256":"6ca2ba61a59f38b715dbb7a4f3f130085dc3a773acb62f408ed8390f2864d0b6","abstract_canon_sha256":"63c3328c5b233a5dedeeb364c0d68cebec02cf81272f78cf3ce90ac237745a25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:29.688424Z","signature_b64":"XMsuNTtR/3Hw/gdk81htwixkcDUm76gODmw82d+wc5shRydKmFjzBe12tMcv9GUQUq1KVfauuKjDMvstlGBUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c16b543655ebaaf36befafa2e9d0da22d016c6ec6cfe7e0b0bb05f5cec3ddb75","last_reissued_at":"2026-07-05T09:50:29.687965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:29.687965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huazhe Xu, Ruizhe Shi, Simon S. Du, Yanjie Ze, Yuyao Liu","submitted_at":"2023-10-31T16:24:17Z","abstract_excerpt":"Offline reinforcement learning (RL) aims to find a near-optimal policy using pre-collected datasets. In real-world scenarios, data collection could be costly and risky; therefore, offline RL becomes particularly challenging when the in-domain data is limited. Given recent advances in Large Language Models (LLMs) and their few-shot learning prowess, this paper introduces $\\textbf{La}$nguage Models for $\\textbf{Mo}$tion Control ($\\textbf{LaMo}$), a general framework based on Decision Transformers to effectively use pre-trained Language Models (LMs) for offline RL. Our framework highlights four c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20587","kind":"arxiv","version":5},"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/2310.20587/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":"2310.20587","created_at":"2026-07-05T09:50:29.688022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.20587v5","created_at":"2026-07-05T09:50:29.688022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20587","created_at":"2026-07-05T09:50:29.688022+00:00"},{"alias_kind":"pith_short_12","alias_value":"YFVVINSV5OVP","created_at":"2026-07-05T09:50:29.688022+00:00"},{"alias_kind":"pith_short_16","alias_value":"YFVVINSV5OVPG27P","created_at":"2026-07-05T09:50:29.688022+00:00"},{"alias_kind":"pith_short_8","alias_value":"YFVVINSV","created_at":"2026-07-05T09:50:29.688022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2409.12514","citing_title":"TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YFVVINSV5OVPG27PV6ROTUG2EL","json":"https://pith.science/pith/YFVVINSV5OVPG27PV6ROTUG2EL.json","graph_json":"https://pith.science/api/pith-number/YFVVINSV5OVPG27PV6ROTUG2EL/graph.json","events_json":"https://pith.science/api/pith-number/YFVVINSV5OVPG27PV6ROTUG2EL/events.json","paper":"https://pith.science/paper/YFVVINSV"},"agent_actions":{"view_html":"https://pith.science/pith/YFVVINSV5OVPG27PV6ROTUG2EL","download_json":"https://pith.science/pith/YFVVINSV5OVPG27PV6ROTUG2EL.json","view_paper":"https://pith.science/paper/YFVVINSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.20587&json=true","fetch_graph":"https://pith.science/api/pith-number/YFVVINSV5OVPG27PV6ROTUG2EL/graph.json","fetch_events":"https://pith.science/api/pith-number/YFVVINSV5OVPG27PV6ROTUG2EL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YFVVINSV5OVPG27PV6ROTUG2EL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YFVVINSV5OVPG27PV6ROTUG2EL/action/storage_attestation","attest_author":"https://pith.science/pith/YFVVINSV5OVPG27PV6ROTUG2EL/action/author_attestation","sign_citation":"https://pith.science/pith/YFVVINSV5OVPG27PV6ROTUG2EL/action/citation_signature","submit_replication":"https://pith.science/pith/YFVVINSV5OVPG27PV6ROTUG2EL/action/replication_record"}},"created_at":"2026-07-05T09:50:29.688022+00:00","updated_at":"2026-07-05T09:50:29.688022+00:00"}