{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VSK3SUVVCS5ZBJRGDO5WUEPYLN","short_pith_number":"pith:VSK3SUVV","schema_version":"1.0","canonical_sha256":"ac95b952b514bb90a6261bbb6a11f85b5e80e37d0ed0df057f2047f34a997168","source":{"kind":"arxiv","id":"2403.06420","version":2},"attestation_state":"computed","paper":{"title":"RLingua: Improving Reinforcement Learning Sample Efficiency in Robotic Manipulations With Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.RO","authors_text":"Liangjun Zhang, Liangliang Chen, Shiyu Jin, Ying Zhang, Yutian Lei","submitted_at":"2024-03-11T04:13:26Z","abstract_excerpt":"Reinforcement learning (RL) has demonstrated its capability in solving various tasks but is notorious for its low sample efficiency. In this paper, we propose RLingua, a framework that can leverage the internal knowledge of large language models (LLMs) to reduce the sample complexity of RL in robotic manipulations. To this end, we first present a method for extracting the prior knowledge of LLMs by prompt engineering so that a preliminary rule-based robot controller for a specific task can be generated in a user-friendly manner. Despite being imperfect, the LLM-generated robot controller is ut"},"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":"2403.06420","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-11T04:13:26Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"d38dadf84c26c3889bc6e894a2cf16db7e64e42a79470c407214d44d4643a41a","abstract_canon_sha256":"8339af71329d6bc46a696ea203da755f37bed92ca4f892a893a691ec2072d7d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:50.913128Z","signature_b64":"cKrnDLdxjDDGkOPp1iYzZR7Dkz2HGqhXD3/FpNfi1jBlH4DFo3PjFObughDy2/A2sk88g0+6pP25/vlHfGi9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac95b952b514bb90a6261bbb6a11f85b5e80e37d0ed0df057f2047f34a997168","last_reissued_at":"2026-07-05T07:57:50.912622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:50.912622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RLingua: Improving Reinforcement Learning Sample Efficiency in Robotic Manipulations With Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.RO","authors_text":"Liangjun Zhang, Liangliang Chen, Shiyu Jin, Ying Zhang, Yutian Lei","submitted_at":"2024-03-11T04:13:26Z","abstract_excerpt":"Reinforcement learning (RL) has demonstrated its capability in solving various tasks but is notorious for its low sample efficiency. In this paper, we propose RLingua, a framework that can leverage the internal knowledge of large language models (LLMs) to reduce the sample complexity of RL in robotic manipulations. To this end, we first present a method for extracting the prior knowledge of LLMs by prompt engineering so that a preliminary rule-based robot controller for a specific task can be generated in a user-friendly manner. Despite being imperfect, the LLM-generated robot controller is ut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06420","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/2403.06420/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":"2403.06420","created_at":"2026-07-05T07:57:50.912685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06420v2","created_at":"2026-07-05T07:57:50.912685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06420","created_at":"2026-07-05T07:57:50.912685+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSK3SUVVCS5Z","created_at":"2026-07-05T07:57:50.912685+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSK3SUVVCS5ZBJRG","created_at":"2026-07-05T07:57:50.912685+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSK3SUVV","created_at":"2026-07-05T07:57:50.912685+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/VSK3SUVVCS5ZBJRGDO5WUEPYLN","json":"https://pith.science/pith/VSK3SUVVCS5ZBJRGDO5WUEPYLN.json","graph_json":"https://pith.science/api/pith-number/VSK3SUVVCS5ZBJRGDO5WUEPYLN/graph.json","events_json":"https://pith.science/api/pith-number/VSK3SUVVCS5ZBJRGDO5WUEPYLN/events.json","paper":"https://pith.science/paper/VSK3SUVV"},"agent_actions":{"view_html":"https://pith.science/pith/VSK3SUVVCS5ZBJRGDO5WUEPYLN","download_json":"https://pith.science/pith/VSK3SUVVCS5ZBJRGDO5WUEPYLN.json","view_paper":"https://pith.science/paper/VSK3SUVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06420&json=true","fetch_graph":"https://pith.science/api/pith-number/VSK3SUVVCS5ZBJRGDO5WUEPYLN/graph.json","fetch_events":"https://pith.science/api/pith-number/VSK3SUVVCS5ZBJRGDO5WUEPYLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSK3SUVVCS5ZBJRGDO5WUEPYLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSK3SUVVCS5ZBJRGDO5WUEPYLN/action/storage_attestation","attest_author":"https://pith.science/pith/VSK3SUVVCS5ZBJRGDO5WUEPYLN/action/author_attestation","sign_citation":"https://pith.science/pith/VSK3SUVVCS5ZBJRGDO5WUEPYLN/action/citation_signature","submit_replication":"https://pith.science/pith/VSK3SUVVCS5ZBJRGDO5WUEPYLN/action/replication_record"}},"created_at":"2026-07-05T07:57:50.912685+00:00","updated_at":"2026-07-05T07:57:50.912685+00:00"}