{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3DUPXATBTF3IPE2XI7S2FDDT4Q","short_pith_number":"pith:3DUPXATB","schema_version":"1.0","canonical_sha256":"d8e8fb8261997687935747e5a28c73e435b708779c83d11efb88b5f5a7e897f3","source":{"kind":"arxiv","id":"2412.16878","version":1},"attestation_state":"computed","paper":{"title":"Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongbin Zhao, Jingbo Sun, Qichao Zhang, Songjun Tu, Xiangyuan Lan","submitted_at":"2024-12-22T06:15:25Z","abstract_excerpt":"Preference-based reinforcement learning (PbRL) provides a powerful paradigm to avoid meticulous reward engineering by learning rewards based on human preferences. However, real-time human feedback is hard to obtain in online tasks. Most work suppose there is a \"scripted teacher\" that utilizes privileged predefined reward to provide preference feedback. In this paper, we propose a RL Self-augmented Large Language Model Feedback (RL-SaLLM-F) technique that does not rely on privileged information for online PbRL. RL-SaLLM-F leverages the reflective and discriminative capabilities of LLM to genera"},"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":"2412.16878","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T06:15:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d5d345f5861896cf85fb44d2f29f6e9b3667ebd353f9804d4d00f0c540d15c52","abstract_canon_sha256":"dab6593acaf491cce2c1748bf6a8161908f87d072e9d8af98afd35dc890efe8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:14.082492Z","signature_b64":"YzOY0SU4FK4e8oxfvE5OKpn6cxCjVmaqp/gJxOxDJbHpG4Emts69wb7qr6PPi7RQE5A1VkcGjaFJTZ64P29jDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8e8fb8261997687935747e5a28c73e435b708779c83d11efb88b5f5a7e897f3","last_reissued_at":"2026-07-05T09:53:14.081948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:14.081948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongbin Zhao, Jingbo Sun, Qichao Zhang, Songjun Tu, Xiangyuan Lan","submitted_at":"2024-12-22T06:15:25Z","abstract_excerpt":"Preference-based reinforcement learning (PbRL) provides a powerful paradigm to avoid meticulous reward engineering by learning rewards based on human preferences. However, real-time human feedback is hard to obtain in online tasks. Most work suppose there is a \"scripted teacher\" that utilizes privileged predefined reward to provide preference feedback. In this paper, we propose a RL Self-augmented Large Language Model Feedback (RL-SaLLM-F) technique that does not rely on privileged information for online PbRL. RL-SaLLM-F leverages the reflective and discriminative capabilities of LLM to genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16878","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/2412.16878/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":"2412.16878","created_at":"2026-07-05T09:53:14.082006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16878v1","created_at":"2026-07-05T09:53:14.082006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16878","created_at":"2026-07-05T09:53:14.082006+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DUPXATBTF3I","created_at":"2026-07-05T09:53:14.082006+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DUPXATBTF3IPE2X","created_at":"2026-07-05T09:53:14.082006+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DUPXATB","created_at":"2026-07-05T09:53:14.082006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25398","citing_title":"MAPL: Multi-Objective Preference Learning for Robot Locomotion","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10564","citing_title":"DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving","ref_index":170,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q","json":"https://pith.science/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q.json","graph_json":"https://pith.science/api/pith-number/3DUPXATBTF3IPE2XI7S2FDDT4Q/graph.json","events_json":"https://pith.science/api/pith-number/3DUPXATBTF3IPE2XI7S2FDDT4Q/events.json","paper":"https://pith.science/paper/3DUPXATB"},"agent_actions":{"view_html":"https://pith.science/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q","download_json":"https://pith.science/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q.json","view_paper":"https://pith.science/paper/3DUPXATB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16878&json=true","fetch_graph":"https://pith.science/api/pith-number/3DUPXATBTF3IPE2XI7S2FDDT4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/3DUPXATBTF3IPE2XI7S2FDDT4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q/action/storage_attestation","attest_author":"https://pith.science/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q/action/author_attestation","sign_citation":"https://pith.science/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q/action/citation_signature","submit_replication":"https://pith.science/pith/3DUPXATBTF3IPE2XI7S2FDDT4Q/action/replication_record"}},"created_at":"2026-07-05T09:53:14.082006+00:00","updated_at":"2026-07-05T09:53:14.082006+00:00"}