{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BINFILZGIXJ5NMPK4X4I3B4CKB","short_pith_number":"pith:BINFILZG","schema_version":"1.0","canonical_sha256":"0a1a542f2645d3d6b1eae5f88d87825064fc81b604967b5c1ceeb20b76f06bb0","source":{"kind":"arxiv","id":"2310.13230","version":5},"attestation_state":"computed","paper":{"title":"Absolute Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Changliu Liu, Feihan Li, Rui Chen, Tianhao Wei, Weiye Zhao, Yifan Sun","submitted_at":"2023-10-20T02:40:05Z","abstract_excerpt":"In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily emphasize improvement in expected performance, lacking the ability to control over the worst-case performance outcomes. To address this limitation, we introduce a novel objective function, optimizing which leads to guaranteed monotonic improvement in the lower probability bound of performance with high confidence. Building upon this groundbreaking theoretical adva"},"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":"2310.13230","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-20T02:40:05Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"992933e375c0703b7f90c3e28c049d9a50c94482ab2dedd88b8ce614d0cc96e0","abstract_canon_sha256":"0ffde96b28448ae14199a5661ce0d206fb3f99d5023ddc5b66a513a6817be620"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:57.919853Z","signature_b64":"0VHrGWbbr8YmBjxK3TLll3u8jCfusrES7AbEHNXodgyBuC74mIMwUraQhR0M0dQfr8uTXnN9RB5tMvW5wm/sBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a1a542f2645d3d6b1eae5f88d87825064fc81b604967b5c1ceeb20b76f06bb0","last_reissued_at":"2026-07-05T08:24:57.919344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:57.919344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Absolute Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Changliu Liu, Feihan Li, Rui Chen, Tianhao Wei, Weiye Zhao, Yifan Sun","submitted_at":"2023-10-20T02:40:05Z","abstract_excerpt":"In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily emphasize improvement in expected performance, lacking the ability to control over the worst-case performance outcomes. To address this limitation, we introduce a novel objective function, optimizing which leads to guaranteed monotonic improvement in the lower probability bound of performance with high confidence. Building upon this groundbreaking theoretical adva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13230","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/2310.13230/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":"2310.13230","created_at":"2026-07-05T08:24:57.919410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.13230v5","created_at":"2026-07-05T08:24:57.919410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13230","created_at":"2026-07-05T08:24:57.919410+00:00"},{"alias_kind":"pith_short_12","alias_value":"BINFILZGIXJ5","created_at":"2026-07-05T08:24:57.919410+00:00"},{"alias_kind":"pith_short_16","alias_value":"BINFILZGIXJ5NMPK","created_at":"2026-07-05T08:24:57.919410+00:00"},{"alias_kind":"pith_short_8","alias_value":"BINFILZG","created_at":"2026-07-05T08:24:57.919410+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/BINFILZGIXJ5NMPK4X4I3B4CKB","json":"https://pith.science/pith/BINFILZGIXJ5NMPK4X4I3B4CKB.json","graph_json":"https://pith.science/api/pith-number/BINFILZGIXJ5NMPK4X4I3B4CKB/graph.json","events_json":"https://pith.science/api/pith-number/BINFILZGIXJ5NMPK4X4I3B4CKB/events.json","paper":"https://pith.science/paper/BINFILZG"},"agent_actions":{"view_html":"https://pith.science/pith/BINFILZGIXJ5NMPK4X4I3B4CKB","download_json":"https://pith.science/pith/BINFILZGIXJ5NMPK4X4I3B4CKB.json","view_paper":"https://pith.science/paper/BINFILZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.13230&json=true","fetch_graph":"https://pith.science/api/pith-number/BINFILZGIXJ5NMPK4X4I3B4CKB/graph.json","fetch_events":"https://pith.science/api/pith-number/BINFILZGIXJ5NMPK4X4I3B4CKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BINFILZGIXJ5NMPK4X4I3B4CKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BINFILZGIXJ5NMPK4X4I3B4CKB/action/storage_attestation","attest_author":"https://pith.science/pith/BINFILZGIXJ5NMPK4X4I3B4CKB/action/author_attestation","sign_citation":"https://pith.science/pith/BINFILZGIXJ5NMPK4X4I3B4CKB/action/citation_signature","submit_replication":"https://pith.science/pith/BINFILZGIXJ5NMPK4X4I3B4CKB/action/replication_record"}},"created_at":"2026-07-05T08:24:57.919410+00:00","updated_at":"2026-07-05T08:24:57.919410+00:00"}