{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:227NWNLEVCHIMQS4GAKCAH5SPZ","short_pith_number":"pith:227NWNLE","schema_version":"1.0","canonical_sha256":"d6bedb3564a88e86425c3014201fb27e782a32120cb14fd131d51d6d9383f8e5","source":{"kind":"arxiv","id":"2309.06687","version":2},"attestation_state":"computed","paper":{"title":"Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chunrong Fang, Jiawei Liu, Jiayang Song, Lei Ma, Zhan Shu, Zhehua Zhou","submitted_at":"2023-09-13T02:56:56Z","abstract_excerpt":"Although Deep Reinforcement Learning (DRL) has achieved notable success in numerous robotic applications, designing a high-performing reward function remains a challenging task that often requires substantial manual input. Recently, Large Language Models (LLMs) have been extensively adopted to address tasks demanding in-depth common-sense knowledge, such as reasoning and planning. Recognizing that reward function design is also inherently linked to such knowledge, LLM offers a promising potential in this context. Motivated by this, we propose in this work a novel LLM framework with a self-refi"},"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":"2309.06687","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-13T02:56:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b373bee2a6cdb7ea7153b22ba0f76d3c5e01a4b67be99f41f3f1fc82e7c60930","abstract_canon_sha256":"f347ff99dfecfcc8beaa6c2ba54beee6b5fbb8ef7771c05d1a773762c8c737b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:22.432457Z","signature_b64":"lkWkIZqkbsQHZDUZksfLy0BCyUH8KUARr8f2Lyte8pP5NbRen3qqk1grYwgUxHffUuVlev4zIwAeFckuBnQyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6bedb3564a88e86425c3014201fb27e782a32120cb14fd131d51d6d9383f8e5","last_reissued_at":"2026-07-05T06:56:22.431998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:22.431998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chunrong Fang, Jiawei Liu, Jiayang Song, Lei Ma, Zhan Shu, Zhehua Zhou","submitted_at":"2023-09-13T02:56:56Z","abstract_excerpt":"Although Deep Reinforcement Learning (DRL) has achieved notable success in numerous robotic applications, designing a high-performing reward function remains a challenging task that often requires substantial manual input. Recently, Large Language Models (LLMs) have been extensively adopted to address tasks demanding in-depth common-sense knowledge, such as reasoning and planning. Recognizing that reward function design is also inherently linked to such knowledge, LLM offers a promising potential in this context. Motivated by this, we propose in this work a novel LLM framework with a self-refi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06687","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/2309.06687/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":"2309.06687","created_at":"2026-07-05T06:56:22.432058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.06687v2","created_at":"2026-07-05T06:56:22.432058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06687","created_at":"2026-07-05T06:56:22.432058+00:00"},{"alias_kind":"pith_short_12","alias_value":"227NWNLEVCHI","created_at":"2026-07-05T06:56:22.432058+00:00"},{"alias_kind":"pith_short_16","alias_value":"227NWNLEVCHIMQS4","created_at":"2026-07-05T06:56:22.432058+00:00"},{"alias_kind":"pith_short_8","alias_value":"227NWNLE","created_at":"2026-07-05T06:56:22.432058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01356","citing_title":"Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/227NWNLEVCHIMQS4GAKCAH5SPZ","json":"https://pith.science/pith/227NWNLEVCHIMQS4GAKCAH5SPZ.json","graph_json":"https://pith.science/api/pith-number/227NWNLEVCHIMQS4GAKCAH5SPZ/graph.json","events_json":"https://pith.science/api/pith-number/227NWNLEVCHIMQS4GAKCAH5SPZ/events.json","paper":"https://pith.science/paper/227NWNLE"},"agent_actions":{"view_html":"https://pith.science/pith/227NWNLEVCHIMQS4GAKCAH5SPZ","download_json":"https://pith.science/pith/227NWNLEVCHIMQS4GAKCAH5SPZ.json","view_paper":"https://pith.science/paper/227NWNLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.06687&json=true","fetch_graph":"https://pith.science/api/pith-number/227NWNLEVCHIMQS4GAKCAH5SPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/227NWNLEVCHIMQS4GAKCAH5SPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/227NWNLEVCHIMQS4GAKCAH5SPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/227NWNLEVCHIMQS4GAKCAH5SPZ/action/storage_attestation","attest_author":"https://pith.science/pith/227NWNLEVCHIMQS4GAKCAH5SPZ/action/author_attestation","sign_citation":"https://pith.science/pith/227NWNLEVCHIMQS4GAKCAH5SPZ/action/citation_signature","submit_replication":"https://pith.science/pith/227NWNLEVCHIMQS4GAKCAH5SPZ/action/replication_record"}},"created_at":"2026-07-05T06:56:22.432058+00:00","updated_at":"2026-07-05T06:56:22.432058+00:00"}