{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:43UYQUIIGC3YOMIA4WW2T4JXFX","short_pith_number":"pith:43UYQUII","schema_version":"1.0","canonical_sha256":"e6e988510830b7873100e5ada9f1372de07e54d7aff4fda2848a0ffa80d726f6","source":{"kind":"arxiv","id":"2412.13492","version":1},"attestation_state":"computed","paper":{"title":"Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Changxin Huang, Jianqiang Li, Junfan Lin, Junyang Liang, Runhao Zeng, Yanbin Chang","submitted_at":"2024-12-18T04:20:33Z","abstract_excerpt":"The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it's challenging to design reward functions for real-world tasks, especially for high-dimensional robotic control, due to complex relationships among joints and tasks. Recent advancements large language models (LLMs) enable automatic reward function design. However, approaches evaluate reward functions by re-training policies from scratch placing an undue burden on the reward functi"},"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":"2412.13492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-18T04:20:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"608dcd298709fc5db4684eceaff6c76a6673fcffd60ef858f9634b8f6c4c11b2","abstract_canon_sha256":"f95062471aa359777a57ae59a7e298e06f1c761ca13ffc964cb2fb9fb51a2bb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:02.724436Z","signature_b64":"56sdhYo7Qv3ZEhd+lNjULHHVhvvq1rSPPi15VAGi4MNMpF6VoDYIA2gTX+jDj8DXBzsq87n9F4iqSXpYDo30Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6e988510830b7873100e5ada9f1372de07e54d7aff4fda2848a0ffa80d726f6","last_reissued_at":"2026-07-05T09:51:02.723848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:02.723848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Changxin Huang, Jianqiang Li, Junfan Lin, Junyang Liang, Runhao Zeng, Yanbin Chang","submitted_at":"2024-12-18T04:20:33Z","abstract_excerpt":"The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it's challenging to design reward functions for real-world tasks, especially for high-dimensional robotic control, due to complex relationships among joints and tasks. Recent advancements large language models (LLMs) enable automatic reward function design. However, approaches evaluate reward functions by re-training policies from scratch placing an undue burden on the reward functi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13492","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/2412.13492/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":"2412.13492","created_at":"2026-07-05T09:51:02.723903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13492v1","created_at":"2026-07-05T09:51:02.723903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13492","created_at":"2026-07-05T09:51:02.723903+00:00"},{"alias_kind":"pith_short_12","alias_value":"43UYQUIIGC3Y","created_at":"2026-07-05T09:51:02.723903+00:00"},{"alias_kind":"pith_short_16","alias_value":"43UYQUIIGC3YOMIA","created_at":"2026-07-05T09:51:02.723903+00:00"},{"alias_kind":"pith_short_8","alias_value":"43UYQUII","created_at":"2026-07-05T09:51:02.723903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/43UYQUIIGC3YOMIA4WW2T4JXFX","json":"https://pith.science/pith/43UYQUIIGC3YOMIA4WW2T4JXFX.json","graph_json":"https://pith.science/api/pith-number/43UYQUIIGC3YOMIA4WW2T4JXFX/graph.json","events_json":"https://pith.science/api/pith-number/43UYQUIIGC3YOMIA4WW2T4JXFX/events.json","paper":"https://pith.science/paper/43UYQUII"},"agent_actions":{"view_html":"https://pith.science/pith/43UYQUIIGC3YOMIA4WW2T4JXFX","download_json":"https://pith.science/pith/43UYQUIIGC3YOMIA4WW2T4JXFX.json","view_paper":"https://pith.science/paper/43UYQUII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13492&json=true","fetch_graph":"https://pith.science/api/pith-number/43UYQUIIGC3YOMIA4WW2T4JXFX/graph.json","fetch_events":"https://pith.science/api/pith-number/43UYQUIIGC3YOMIA4WW2T4JXFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43UYQUIIGC3YOMIA4WW2T4JXFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43UYQUIIGC3YOMIA4WW2T4JXFX/action/storage_attestation","attest_author":"https://pith.science/pith/43UYQUIIGC3YOMIA4WW2T4JXFX/action/author_attestation","sign_citation":"https://pith.science/pith/43UYQUIIGC3YOMIA4WW2T4JXFX/action/citation_signature","submit_replication":"https://pith.science/pith/43UYQUIIGC3YOMIA4WW2T4JXFX/action/replication_record"}},"created_at":"2026-07-05T09:51:02.723903+00:00","updated_at":"2026-07-05T09:51:02.723903+00:00"}