{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:M4JBL7KLWW6GPSCVS2MZUJZHVN","short_pith_number":"pith:M4JBL7KL","schema_version":"1.0","canonical_sha256":"671215fd4bb5bc67c85596999a2727ab77aa3e74bc337ee574cf3e9b3db54833","source":{"kind":"arxiv","id":"2006.05961","version":2},"attestation_state":"computed","paper":{"title":"Model-Free Algorithm and Regret Analysis for MDPs with Long-Term Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NI","cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ather Gattami, Qinbo Bai, Vaneet Aggarwal","submitted_at":"2020-06-10T17:19:29Z","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"},"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":"2006.05961","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T17:19:29Z","cross_cats_sorted":["cs.NI","cs.SY","eess.SY","math.OC","stat.ML"],"title_canon_sha256":"5b1962346fb1a1c81c0bdbcde98a126fe8c4a6788944bd9ec350897b1a6e6e27","abstract_canon_sha256":"21ed70bc439f213061199a874cd5d92f131321b0f0dcf879415e6271d65dc018"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:11:01.098848Z","signature_b64":"AoPeAJZoRJpben7Z0xfbMsIc6TllRxaHclCA4B9cImPpIuYcJmaWjNU4CcHpNi4t8URWKNpR+wYly6yxrC8DAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"671215fd4bb5bc67c85596999a2727ab77aa3e74bc337ee574cf3e9b3db54833","last_reissued_at":"2026-07-05T02:11:01.098272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:11:01.098272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Free Algorithm and Regret Analysis for MDPs with Long-Term Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NI","cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ather Gattami, Qinbo Bai, Vaneet Aggarwal","submitted_at":"2020-06-10T17:19:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05961","kind":"arxiv","version":2},"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/2006.05961/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":"2006.05961","created_at":"2026-07-05T02:11:01.098349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.05961v2","created_at":"2026-07-05T02:11:01.098349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05961","created_at":"2026-07-05T02:11:01.098349+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4JBL7KLWW6G","created_at":"2026-07-05T02:11:01.098349+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4JBL7KLWW6GPSCV","created_at":"2026-07-05T02:11:01.098349+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4JBL7KL","created_at":"2026-07-05T02:11:01.098349+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10519","citing_title":"Online Resource Allocation With General Constraints","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08290","citing_title":"Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M4JBL7KLWW6GPSCVS2MZUJZHVN","json":"https://pith.science/pith/M4JBL7KLWW6GPSCVS2MZUJZHVN.json","graph_json":"https://pith.science/api/pith-number/M4JBL7KLWW6GPSCVS2MZUJZHVN/graph.json","events_json":"https://pith.science/api/pith-number/M4JBL7KLWW6GPSCVS2MZUJZHVN/events.json","paper":"https://pith.science/paper/M4JBL7KL"},"agent_actions":{"view_html":"https://pith.science/pith/M4JBL7KLWW6GPSCVS2MZUJZHVN","download_json":"https://pith.science/pith/M4JBL7KLWW6GPSCVS2MZUJZHVN.json","view_paper":"https://pith.science/paper/M4JBL7KL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.05961&json=true","fetch_graph":"https://pith.science/api/pith-number/M4JBL7KLWW6GPSCVS2MZUJZHVN/graph.json","fetch_events":"https://pith.science/api/pith-number/M4JBL7KLWW6GPSCVS2MZUJZHVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4JBL7KLWW6GPSCVS2MZUJZHVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4JBL7KLWW6GPSCVS2MZUJZHVN/action/storage_attestation","attest_author":"https://pith.science/pith/M4JBL7KLWW6GPSCVS2MZUJZHVN/action/author_attestation","sign_citation":"https://pith.science/pith/M4JBL7KLWW6GPSCVS2MZUJZHVN/action/citation_signature","submit_replication":"https://pith.science/pith/M4JBL7KLWW6GPSCVS2MZUJZHVN/action/replication_record"}},"created_at":"2026-07-05T02:11:01.098349+00:00","updated_at":"2026-07-05T02:11:01.098349+00:00"}