{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KDJITFRCVSQTRDTT3OFIXQKOGY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"734afa8906bae8b59fa234cdd0aef9e06c0923532f0132b0eb6809169fb840b8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T00:23:36Z","title_canon_sha256":"d6684c559ed46bf3365e7b7e381507338787c857b5ed46d223c53bdee2583953"},"schema_version":"1.0","source":{"id":"2302.00808","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.00808","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"arxiv_version","alias_value":"2302.00808v4","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00808","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"pith_short_12","alias_value":"KDJITFRCVSQT","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"pith_short_16","alias_value":"KDJITFRCVSQTRDTT","created_at":"2026-07-05T08:22:30Z"},{"alias_kind":"pith_short_8","alias_value":"KDJITFRC","created_at":"2026-07-05T08:22:30Z"}],"graph_snapshots":[{"event_id":"sha256:544bb69b10008ed2b4a90b332300068c626963a616828d81da610a17e53c59fe","target":"graph","created_at":"2026-07-05T08:22:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.00808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Akhil Agnihotri, Haipeng Luo, Rahul Jain","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T00:23:36Z","title":"ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00808","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6cfd2f75bdf8517b83296621a4693326feed2d2b89bb893c8420f319a6cdd03b","target":"record","created_at":"2026-07-05T08:22:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"734afa8906bae8b59fa234cdd0aef9e06c0923532f0132b0eb6809169fb840b8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T00:23:36Z","title_canon_sha256":"d6684c559ed46bf3365e7b7e381507338787c857b5ed46d223c53bdee2583953"},"schema_version":"1.0","source":{"id":"2302.00808","kind":"arxiv","version":4}},"canonical_sha256":"50d2899622aca1388e73db8a8bc14e361a4355b472efd042295a0646a9343f51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50d2899622aca1388e73db8a8bc14e361a4355b472efd042295a0646a9343f51","first_computed_at":"2026-07-05T08:22:30.843500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:30.843500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fEkcHY8BskOfMJ89mSKBhsBvGZwkpLUICTU4T99zfH01KhHOAGAmSMj0hIIGBKw9d1JhXztuxadxBg8A83CAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:30.844027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.00808","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cfd2f75bdf8517b83296621a4693326feed2d2b89bb893c8420f319a6cdd03b","sha256:544bb69b10008ed2b4a90b332300068c626963a616828d81da610a17e53c59fe"],"state_sha256":"9fe61b6877c6ffc5c9087f5f1a978f9c2d412b13ea9fce07e27c463be3a9c45d"}