{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:M4JBL7KLWW6GPSCVS2MZUJZHVN","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":"21ed70bc439f213061199a874cd5d92f131321b0f0dcf879415e6271d65dc018","cross_cats_sorted":["cs.NI","cs.SY","eess.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T17:19:29Z","title_canon_sha256":"5b1962346fb1a1c81c0bdbcde98a126fe8c4a6788944bd9ec350897b1a6e6e27"},"schema_version":"1.0","source":{"id":"2006.05961","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.05961","created_at":"2026-07-05T02:11:01Z"},{"alias_kind":"arxiv_version","alias_value":"2006.05961v2","created_at":"2026-07-05T02:11:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05961","created_at":"2026-07-05T02:11:01Z"},{"alias_kind":"pith_short_12","alias_value":"M4JBL7KLWW6G","created_at":"2026-07-05T02:11:01Z"},{"alias_kind":"pith_short_16","alias_value":"M4JBL7KLWW6GPSCV","created_at":"2026-07-05T02:11:01Z"},{"alias_kind":"pith_short_8","alias_value":"M4JBL7KL","created_at":"2026-07-05T02:11:01Z"}],"graph_snapshots":[{"event_id":"sha256:dd19b794e59c5b13d9d892eba2a7937eaa99e659bbbc9dd6614714ac4b173570","target":"graph","created_at":"2026-07-05T02:11:01Z","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/2006.05961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the optimization of dynamical systems, the variables typically have constraints. Such problems can be modeled as a constrained Markov Decision Process (CMDP). This paper considers a model-free approach to the problem, where the transition probabilities are not known. In the presence of long-term (or average) constraints, the agent has to choose a policy that maximizes the long-term average reward as well as satisfy the average constraints in each episode. The key challenge with the long-term constraints is that the optimal policy is not deterministic in general, and thus standard Q-learning","authors_text":"Ather Gattami, Qinbo Bai, Vaneet Aggarwal","cross_cats":["cs.NI","cs.SY","eess.SY","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T17:19:29Z","title":"Model-Free Algorithm and Regret Analysis for MDPs with Long-Term Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05961","kind":"arxiv","version":2},"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:c4220c6c0e15142d9519c5089a946e22134e237bce718f2040424a070115c943","target":"record","created_at":"2026-07-05T02:11:01Z","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":"21ed70bc439f213061199a874cd5d92f131321b0f0dcf879415e6271d65dc018","cross_cats_sorted":["cs.NI","cs.SY","eess.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T17:19:29Z","title_canon_sha256":"5b1962346fb1a1c81c0bdbcde98a126fe8c4a6788944bd9ec350897b1a6e6e27"},"schema_version":"1.0","source":{"id":"2006.05961","kind":"arxiv","version":2}},"canonical_sha256":"671215fd4bb5bc67c85596999a2727ab77aa3e74bc337ee574cf3e9b3db54833","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"671215fd4bb5bc67c85596999a2727ab77aa3e74bc337ee574cf3e9b3db54833","first_computed_at":"2026-07-05T02:11:01.098272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:11:01.098272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AoPeAJZoRJpben7Z0xfbMsIc6TllRxaHclCA4B9cImPpIuYcJmaWjNU4CcHpNi4t8URWKNpR+wYly6yxrC8DAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:11:01.098848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.05961","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4220c6c0e15142d9519c5089a946e22134e237bce718f2040424a070115c943","sha256:dd19b794e59c5b13d9d892eba2a7937eaa99e659bbbc9dd6614714ac4b173570"],"state_sha256":"9ca3d2f4288270e2b2e95cfc23d9d074c3a41e3dfd63400f316d9bdf225eb6d9"}