{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KDJITFRCVSQTRDTT3OFIXQKOGY","short_pith_number":"pith:KDJITFRC","schema_version":"1.0","canonical_sha256":"50d2899622aca1388e73db8a8bc14e361a4355b472efd042295a0646a9343f51","source":{"kind":"arxiv","id":"2302.00808","version":4},"attestation_state":"computed","paper":{"title":"ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akhil Agnihotri, Haipeng Luo, Rahul Jain","submitted_at":"2023-02-02T00:23:36Z","abstract_excerpt":"Reinforcement Learning (RL) for constrained MDPs (CMDPs) is an increasingly important problem for various applications. Often, the average criterion is more suitable than the discounted criterion. Yet, RL for average-CMDPs (ACMDPs) remains a challenging problem. Algorithms designed for discounted constrained RL problems often do not perform well for the average CMDP setting. In this paper, we introduce a new policy optimization with function approximation algorithm for constrained MDPs with the average criterion. The Average-Constrained Policy Optimization (ACPO) algorithm is inspired by trust"},"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":"2302.00808","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T00:23:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6684c559ed46bf3365e7b7e381507338787c857b5ed46d223c53bdee2583953","abstract_canon_sha256":"734afa8906bae8b59fa234cdd0aef9e06c0923532f0132b0eb6809169fb840b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:30.844027Z","signature_b64":"fEkcHY8BskOfMJ89mSKBhsBvGZwkpLUICTU4T99zfH01KhHOAGAmSMj0hIIGBKw9d1JhXztuxadxBg8A83CAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50d2899622aca1388e73db8a8bc14e361a4355b472efd042295a0646a9343f51","last_reissued_at":"2026-07-05T08:22:30.843500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:30.843500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akhil Agnihotri, Haipeng Luo, Rahul Jain","submitted_at":"2023-02-02T00:23:36Z","abstract_excerpt":"Reinforcement Learning (RL) for constrained MDPs (CMDPs) is an increasingly important problem for various applications. Often, the average criterion is more suitable than the discounted criterion. Yet, RL for average-CMDPs (ACMDPs) remains a challenging problem. Algorithms designed for discounted constrained RL problems often do not perform well for the average CMDP setting. In this paper, we introduce a new policy optimization with function approximation algorithm for constrained MDPs with the average criterion. The Average-Constrained Policy Optimization (ACPO) algorithm is inspired by trust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00808","kind":"arxiv","version":4},"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/2302.00808/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":"2302.00808","created_at":"2026-07-05T08:22:30.843560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.00808v4","created_at":"2026-07-05T08:22:30.843560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00808","created_at":"2026-07-05T08:22:30.843560+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDJITFRCVSQT","created_at":"2026-07-05T08:22:30.843560+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDJITFRCVSQTRDTT","created_at":"2026-07-05T08:22:30.843560+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDJITFRC","created_at":"2026-07-05T08:22:30.843560+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/KDJITFRCVSQTRDTT3OFIXQKOGY","json":"https://pith.science/pith/KDJITFRCVSQTRDTT3OFIXQKOGY.json","graph_json":"https://pith.science/api/pith-number/KDJITFRCVSQTRDTT3OFIXQKOGY/graph.json","events_json":"https://pith.science/api/pith-number/KDJITFRCVSQTRDTT3OFIXQKOGY/events.json","paper":"https://pith.science/paper/KDJITFRC"},"agent_actions":{"view_html":"https://pith.science/pith/KDJITFRCVSQTRDTT3OFIXQKOGY","download_json":"https://pith.science/pith/KDJITFRCVSQTRDTT3OFIXQKOGY.json","view_paper":"https://pith.science/paper/KDJITFRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.00808&json=true","fetch_graph":"https://pith.science/api/pith-number/KDJITFRCVSQTRDTT3OFIXQKOGY/graph.json","fetch_events":"https://pith.science/api/pith-number/KDJITFRCVSQTRDTT3OFIXQKOGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDJITFRCVSQTRDTT3OFIXQKOGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDJITFRCVSQTRDTT3OFIXQKOGY/action/storage_attestation","attest_author":"https://pith.science/pith/KDJITFRCVSQTRDTT3OFIXQKOGY/action/author_attestation","sign_citation":"https://pith.science/pith/KDJITFRCVSQTRDTT3OFIXQKOGY/action/citation_signature","submit_replication":"https://pith.science/pith/KDJITFRCVSQTRDTT3OFIXQKOGY/action/replication_record"}},"created_at":"2026-07-05T08:22:30.843560+00:00","updated_at":"2026-07-05T08:22:30.843560+00:00"}