{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZR7CVTWRU6UPWC6KUHW64YGQQ2","short_pith_number":"pith:ZR7CVTWR","canonical_record":{"source":{"id":"2003.05555","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-03-11T23:23:29Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"d77af39c96709f2c5cff1c38a905525843b748fab37c60cd69b1ea72f2808388","abstract_canon_sha256":"4c4dc4f956607eb7a824f258172131f0ea65b515944345f0187a8b073e0b96e5"},"schema_version":"1.0"},"canonical_sha256":"cc7e2aced1a7a8fb0bcaa1edee60d086b465f0fafb67e5a5ad45c941d5b1c1ef","source":{"kind":"arxiv","id":"2003.05555","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.05555","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"arxiv_version","alias_value":"2003.05555v6","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.05555","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"pith_short_12","alias_value":"ZR7CVTWRU6UP","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"pith_short_16","alias_value":"ZR7CVTWRU6UPWC6K","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"pith_short_8","alias_value":"ZR7CVTWR","created_at":"2026-07-05T04:31:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZR7CVTWRU6UPWC6KUHW64YGQQ2","target":"record","payload":{"canonical_record":{"source":{"id":"2003.05555","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-03-11T23:23:29Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"d77af39c96709f2c5cff1c38a905525843b748fab37c60cd69b1ea72f2808388","abstract_canon_sha256":"4c4dc4f956607eb7a824f258172131f0ea65b515944345f0187a8b073e0b96e5"},"schema_version":"1.0"},"canonical_sha256":"cc7e2aced1a7a8fb0bcaa1edee60d086b465f0fafb67e5a5ad45c941d5b1c1ef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:19.413448Z","signature_b64":"a6ADVikMP7XEX2IO78sANBVWFEK1gJtUuFcRhd3gPLIL2O9273lQrjSc2mtZbabKIyNxYaFRxbMZOd7UJdgwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc7e2aced1a7a8fb0bcaa1edee60d086b465f0fafb67e5a5ad45c941d5b1c1ef","last_reissued_at":"2026-07-05T04:31:19.412940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:19.412940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.05555","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:31:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qc7sGg8+UL81Y9Bj2Vd2ddlBvmAy+SRLm2jb6U9Oa1/efZYvZ5c73s9+3B4TOkVm1YqBzQAVxOmTE+z5mo2HBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:17:36.383799Z"},"content_sha256":"4d25aec6fa5c3ff35006cf9baa40c5100f5288141d6bf846422c054a7addc644","schema_version":"1.0","event_id":"sha256:4d25aec6fa5c3ff35006cf9baa40c5100f5288141d6bf846422c054a7addc644"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZR7CVTWRU6UPWC6KUHW64YGQQ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Efficient Model-Free Algorithm for MDPs with Peak Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY","stat.ML"],"primary_cat":"math.OC","authors_text":"Ather Gattami, Qinbo Bai, Vaneet Aggarwal","submitted_at":"2020-03-11T23:23:29Z","abstract_excerpt":"In the optimization of dynamic systems, the variables typically have constraints. Such problems can be modeled as a Constrained Markov Decision Process (CMDP). This paper considers the peak Constrained Markov Decision Process (PCMDP), where the agent chooses the policy to maximize total reward in the finite horizon as well as satisfy constraints at each epoch with probability 1. We propose a model-free algorithm that converts PCMDP problem to an unconstrained problem and a Q-learning based approach is applied. We define the concept of probably approximately correct (PAC) to the proposed PCMDP "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.05555","kind":"arxiv","version":6},"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/2003.05555/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:31:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wQvh5FXwAPgf0cnZrGylrV386hVZNvxusIaG7NJIELr+RX1MqoUMb4aOB48HLjBdpvEda2vg3RKsuDFG6PffCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:17:36.384329Z"},"content_sha256":"1a5985c46d0ba0be134a42beaa35a5018f4807e6c561783810e972c41a0c8ba3","schema_version":"1.0","event_id":"sha256:1a5985c46d0ba0be134a42beaa35a5018f4807e6c561783810e972c41a0c8ba3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZR7CVTWRU6UPWC6KUHW64YGQQ2/bundle.json","state_url":"https://pith.science/pith/ZR7CVTWRU6UPWC6KUHW64YGQQ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZR7CVTWRU6UPWC6KUHW64YGQQ2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T11:17:36Z","links":{"resolver":"https://pith.science/pith/ZR7CVTWRU6UPWC6KUHW64YGQQ2","bundle":"https://pith.science/pith/ZR7CVTWRU6UPWC6KUHW64YGQQ2/bundle.json","state":"https://pith.science/pith/ZR7CVTWRU6UPWC6KUHW64YGQQ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZR7CVTWRU6UPWC6KUHW64YGQQ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZR7CVTWRU6UPWC6KUHW64YGQQ2","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":"4c4dc4f956607eb7a824f258172131f0ea65b515944345f0187a8b073e0b96e5","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-03-11T23:23:29Z","title_canon_sha256":"d77af39c96709f2c5cff1c38a905525843b748fab37c60cd69b1ea72f2808388"},"schema_version":"1.0","source":{"id":"2003.05555","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.05555","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"arxiv_version","alias_value":"2003.05555v6","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.05555","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"pith_short_12","alias_value":"ZR7CVTWRU6UP","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"pith_short_16","alias_value":"ZR7CVTWRU6UPWC6K","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"pith_short_8","alias_value":"ZR7CVTWR","created_at":"2026-07-05T04:31:19Z"}],"graph_snapshots":[{"event_id":"sha256:1a5985c46d0ba0be134a42beaa35a5018f4807e6c561783810e972c41a0c8ba3","target":"graph","created_at":"2026-07-05T04:31:19Z","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/2003.05555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the optimization of dynamic systems, the variables typically have constraints. Such problems can be modeled as a Constrained Markov Decision Process (CMDP). This paper considers the peak Constrained Markov Decision Process (PCMDP), where the agent chooses the policy to maximize total reward in the finite horizon as well as satisfy constraints at each epoch with probability 1. We propose a model-free algorithm that converts PCMDP problem to an unconstrained problem and a Q-learning based approach is applied. We define the concept of probably approximately correct (PAC) to the proposed PCMDP ","authors_text":"Ather Gattami, Qinbo Bai, Vaneet Aggarwal","cross_cats":["cs.LG","cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-03-11T23:23:29Z","title":"Provably Efficient Model-Free Algorithm for MDPs with Peak Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.05555","kind":"arxiv","version":6},"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":"sha256:4d25aec6fa5c3ff35006cf9baa40c5100f5288141d6bf846422c054a7addc644","target":"record","created_at":"2026-07-05T04:31:19Z","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":"4c4dc4f956607eb7a824f258172131f0ea65b515944345f0187a8b073e0b96e5","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-03-11T23:23:29Z","title_canon_sha256":"d77af39c96709f2c5cff1c38a905525843b748fab37c60cd69b1ea72f2808388"},"schema_version":"1.0","source":{"id":"2003.05555","kind":"arxiv","version":6}},"canonical_sha256":"cc7e2aced1a7a8fb0bcaa1edee60d086b465f0fafb67e5a5ad45c941d5b1c1ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc7e2aced1a7a8fb0bcaa1edee60d086b465f0fafb67e5a5ad45c941d5b1c1ef","first_computed_at":"2026-07-05T04:31:19.412940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:31:19.412940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a6ADVikMP7XEX2IO78sANBVWFEK1gJtUuFcRhd3gPLIL2O9273lQrjSc2mtZbabKIyNxYaFRxbMZOd7UJdgwCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:31:19.413448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.05555","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d25aec6fa5c3ff35006cf9baa40c5100f5288141d6bf846422c054a7addc644","sha256:1a5985c46d0ba0be134a42beaa35a5018f4807e6c561783810e972c41a0c8ba3"],"state_sha256":"8e9740b068c53007323eaad0e71de88899dec22c1edab2cb76cf0412368bde79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q//CqtbTGAk2HIxzXNqjcroMe999mYBeqvyWE+xEu7jbWkwaLVbFnVEWI7UUgzfI7uGunxYYknDrYfvqJrzEAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:17:36.388345Z","bundle_sha256":"d76a1f3673cd96e2d2669d83cb0ff8c2592e435a9d07cb810cba056eb76f215d"}}