{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5YAHRCE6EUFLGNWQRMUUOWKMJ7","short_pith_number":"pith:5YAHRCE6","schema_version":"1.0","canonical_sha256":"ee0078889e250ab336d08b2947594c4fcad5515809ea17adcd5984f6b4e37183","source":{"kind":"arxiv","id":"2109.06332","version":3},"attestation_state":"computed","paper":{"title":"Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alec Koppel, Amrit Singh Bedi, Mridul Agarwal, Qinbo Bai, Vaneet Aggarwal","submitted_at":"2021-09-13T21:27:03Z","abstract_excerpt":"Reinforcement learning is widely used in applications where one needs to perform sequential decisions while interacting with the environment. The problem becomes more challenging when the decision requirement includes satisfying some safety constraints. The problem is mathematically formulated as constrained Markov decision process (CMDP). In the literature, various algorithms are available to solve CMDP problems in a model-free manner to achieve $\\epsilon$-optimal cumulative reward with $\\epsilon$ feasible policies. An $\\epsilon$-feasible policy implies that it suffers from constraint violati"},"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":"2109.06332","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-13T21:27:03Z","cross_cats_sorted":[],"title_canon_sha256":"89ad5cadf0cb67f37bebb01e5e97e51b0647232132526caf1acddf192779a5af","abstract_canon_sha256":"28c9fa5dabc6708195976b3ac24b5de781bdf5694e757a336ebcae89a6b8e482"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:07.658461Z","signature_b64":"07ZKiuPLto5p3L6xYYOBCYLsRQxpJPsYZ6l5ZBMNLN1FA9JYKcoMnVojgEWsrfRkZB389wO1FOjEm4urh5mRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee0078889e250ab336d08b2947594c4fcad5515809ea17adcd5984f6b4e37183","last_reissued_at":"2026-07-05T04:40:07.658040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:07.658040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alec Koppel, Amrit Singh Bedi, Mridul Agarwal, Qinbo Bai, Vaneet Aggarwal","submitted_at":"2021-09-13T21:27:03Z","abstract_excerpt":"Reinforcement learning is widely used in applications where one needs to perform sequential decisions while interacting with the environment. The problem becomes more challenging when the decision requirement includes satisfying some safety constraints. The problem is mathematically formulated as constrained Markov decision process (CMDP). In the literature, various algorithms are available to solve CMDP problems in a model-free manner to achieve $\\epsilon$-optimal cumulative reward with $\\epsilon$ feasible policies. An $\\epsilon$-feasible policy implies that it suffers from constraint violati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06332","kind":"arxiv","version":3},"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/2109.06332/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":"2109.06332","created_at":"2026-07-05T04:40:07.658148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.06332v3","created_at":"2026-07-05T04:40:07.658148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06332","created_at":"2026-07-05T04:40:07.658148+00:00"},{"alias_kind":"pith_short_12","alias_value":"5YAHRCE6EUFL","created_at":"2026-07-05T04:40:07.658148+00:00"},{"alias_kind":"pith_short_16","alias_value":"5YAHRCE6EUFLGNWQ","created_at":"2026-07-05T04:40:07.658148+00:00"},{"alias_kind":"pith_short_8","alias_value":"5YAHRCE6","created_at":"2026-07-05T04:40:07.658148+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/5YAHRCE6EUFLGNWQRMUUOWKMJ7","json":"https://pith.science/pith/5YAHRCE6EUFLGNWQRMUUOWKMJ7.json","graph_json":"https://pith.science/api/pith-number/5YAHRCE6EUFLGNWQRMUUOWKMJ7/graph.json","events_json":"https://pith.science/api/pith-number/5YAHRCE6EUFLGNWQRMUUOWKMJ7/events.json","paper":"https://pith.science/paper/5YAHRCE6"},"agent_actions":{"view_html":"https://pith.science/pith/5YAHRCE6EUFLGNWQRMUUOWKMJ7","download_json":"https://pith.science/pith/5YAHRCE6EUFLGNWQRMUUOWKMJ7.json","view_paper":"https://pith.science/paper/5YAHRCE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.06332&json=true","fetch_graph":"https://pith.science/api/pith-number/5YAHRCE6EUFLGNWQRMUUOWKMJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/5YAHRCE6EUFLGNWQRMUUOWKMJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5YAHRCE6EUFLGNWQRMUUOWKMJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5YAHRCE6EUFLGNWQRMUUOWKMJ7/action/storage_attestation","attest_author":"https://pith.science/pith/5YAHRCE6EUFLGNWQRMUUOWKMJ7/action/author_attestation","sign_citation":"https://pith.science/pith/5YAHRCE6EUFLGNWQRMUUOWKMJ7/action/citation_signature","submit_replication":"https://pith.science/pith/5YAHRCE6EUFLGNWQRMUUOWKMJ7/action/replication_record"}},"created_at":"2026-07-05T04:40:07.658148+00:00","updated_at":"2026-07-05T04:40:07.658148+00:00"}