{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4APG6YXTEBEVWHLPMPHAFU72HQ","short_pith_number":"pith:4APG6YXT","canonical_record":{"source":{"id":"2003.02189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-04T17:03:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5957b88ef595cb4fd396919fd67577e8582e66229e09c23c3da6228c2fbf62a5","abstract_canon_sha256":"581a9385a13e507ff9ec1061d8b1d610407edbbb966ff33c5be2700fc743a1a0"},"schema_version":"1.0"},"canonical_sha256":"e01e6f62f320495b1d6f63ce02d3fa3c02fb2f79468c5dcd500273b9e3a4415b","source":{"kind":"arxiv","id":"2003.02189","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.02189","created_at":"2026-07-05T00:45:47Z"},{"alias_kind":"arxiv_version","alias_value":"2003.02189v1","created_at":"2026-07-05T00:45:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.02189","created_at":"2026-07-05T00:45:47Z"},{"alias_kind":"pith_short_12","alias_value":"4APG6YXTEBEV","created_at":"2026-07-05T00:45:47Z"},{"alias_kind":"pith_short_16","alias_value":"4APG6YXTEBEVWHLP","created_at":"2026-07-05T00:45:47Z"},{"alias_kind":"pith_short_8","alias_value":"4APG6YXT","created_at":"2026-07-05T00:45:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4APG6YXTEBEVWHLPMPHAFU72HQ","target":"record","payload":{"canonical_record":{"source":{"id":"2003.02189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-04T17:03:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5957b88ef595cb4fd396919fd67577e8582e66229e09c23c3da6228c2fbf62a5","abstract_canon_sha256":"581a9385a13e507ff9ec1061d8b1d610407edbbb966ff33c5be2700fc743a1a0"},"schema_version":"1.0"},"canonical_sha256":"e01e6f62f320495b1d6f63ce02d3fa3c02fb2f79468c5dcd500273b9e3a4415b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:45:47.746751Z","signature_b64":"fLyrbELvVEjaebML8HbGi3CY8zP6V4OewGZaROqWDf9YeJ69cQ1DUBdf9HrQqmSolAPSUhpd1Sy/cKUTY7lNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e01e6f62f320495b1d6f63ce02d3fa3c02fb2f79468c5dcd500273b9e3a4415b","last_reissued_at":"2026-07-05T00:45:47.746255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:45:47.746255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.02189","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:45:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E/gJwvMWLgjT7c3Ln7UknvikqPmow4aP4NTuIenlDEA4uds8Z7B6C9zQ/ACh3MsAHwrFk1izNL/dhswplQA+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:16:53.236523Z"},"content_sha256":"b609b3ae0055f150b5cfea5cf4f1fdebdaa4fe96c878d65b34ac4f685fd93c8a","schema_version":"1.0","event_id":"sha256:b609b3ae0055f150b5cfea5cf4f1fdebdaa4fe96c878d65b34ac4f685fd93c8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4APG6YXTEBEVWHLPMPHAFU72HQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploration-Exploitation in Constrained MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Matteo Pirotta, Shie Mannor, Yonathan Efroni","submitted_at":"2020-03-04T17:03:56Z","abstract_excerpt":"In many sequential decision-making problems, the goal is to optimize a utility function while satisfying a set of constraints on different utilities. This learning problem is formalized through Constrained Markov Decision Processes (CMDPs). In this paper, we investigate the exploration-exploitation dilemma in CMDPs. While learning in an unknown CMDP, an agent should trade-off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward while satisfying the constraints. While the agent will eventually learn a good or optimal policy, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.02189","kind":"arxiv","version":1},"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/2003.02189/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":"2026-07-05T00:45:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ta1hpvZsX54F4GYTINPpq3TVqDVdEFmXQrNza1Pu2c5FTlYzpryS5wmFFmpUFBeakw4ts3kI9MXAqFnhYZ/kBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:16:53.237047Z"},"content_sha256":"cb540e5efc308da2f2792191f0f4749ca9292fb4de2621eec22e3e637f3812ba","schema_version":"1.0","event_id":"sha256:cb540e5efc308da2f2792191f0f4749ca9292fb4de2621eec22e3e637f3812ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4APG6YXTEBEVWHLPMPHAFU72HQ/bundle.json","state_url":"https://pith.science/pith/4APG6YXTEBEVWHLPMPHAFU72HQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4APG6YXTEBEVWHLPMPHAFU72HQ/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":"2026-08-05T15:16:53Z","links":{"resolver":"https://pith.science/pith/4APG6YXTEBEVWHLPMPHAFU72HQ","bundle":"https://pith.science/pith/4APG6YXTEBEVWHLPMPHAFU72HQ/bundle.json","state":"https://pith.science/pith/4APG6YXTEBEVWHLPMPHAFU72HQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4APG6YXTEBEVWHLPMPHAFU72HQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4APG6YXTEBEVWHLPMPHAFU72HQ","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":"581a9385a13e507ff9ec1061d8b1d610407edbbb966ff33c5be2700fc743a1a0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-04T17:03:56Z","title_canon_sha256":"5957b88ef595cb4fd396919fd67577e8582e66229e09c23c3da6228c2fbf62a5"},"schema_version":"1.0","source":{"id":"2003.02189","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.02189","created_at":"2026-07-05T00:45:47Z"},{"alias_kind":"arxiv_version","alias_value":"2003.02189v1","created_at":"2026-07-05T00:45:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.02189","created_at":"2026-07-05T00:45:47Z"},{"alias_kind":"pith_short_12","alias_value":"4APG6YXTEBEV","created_at":"2026-07-05T00:45:47Z"},{"alias_kind":"pith_short_16","alias_value":"4APG6YXTEBEVWHLP","created_at":"2026-07-05T00:45:47Z"},{"alias_kind":"pith_short_8","alias_value":"4APG6YXT","created_at":"2026-07-05T00:45:47Z"}],"graph_snapshots":[{"event_id":"sha256:cb540e5efc308da2f2792191f0f4749ca9292fb4de2621eec22e3e637f3812ba","target":"graph","created_at":"2026-07-05T00:45:47Z","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/2003.02189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many sequential decision-making problems, the goal is to optimize a utility function while satisfying a set of constraints on different utilities. This learning problem is formalized through Constrained Markov Decision Processes (CMDPs). In this paper, we investigate the exploration-exploitation dilemma in CMDPs. While learning in an unknown CMDP, an agent should trade-off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward while satisfying the constraints. While the agent will eventually learn a good or optimal policy, we ","authors_text":"Matteo Pirotta, Shie Mannor, Yonathan Efroni","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-04T17:03:56Z","title":"Exploration-Exploitation in Constrained MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.02189","kind":"arxiv","version":1},"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:b609b3ae0055f150b5cfea5cf4f1fdebdaa4fe96c878d65b34ac4f685fd93c8a","target":"record","created_at":"2026-07-05T00:45:47Z","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":"581a9385a13e507ff9ec1061d8b1d610407edbbb966ff33c5be2700fc743a1a0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-04T17:03:56Z","title_canon_sha256":"5957b88ef595cb4fd396919fd67577e8582e66229e09c23c3da6228c2fbf62a5"},"schema_version":"1.0","source":{"id":"2003.02189","kind":"arxiv","version":1}},"canonical_sha256":"e01e6f62f320495b1d6f63ce02d3fa3c02fb2f79468c5dcd500273b9e3a4415b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e01e6f62f320495b1d6f63ce02d3fa3c02fb2f79468c5dcd500273b9e3a4415b","first_computed_at":"2026-07-05T00:45:47.746255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:45:47.746255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fLyrbELvVEjaebML8HbGi3CY8zP6V4OewGZaROqWDf9YeJ69cQ1DUBdf9HrQqmSolAPSUhpd1Sy/cKUTY7lNCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:45:47.746751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.02189","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b609b3ae0055f150b5cfea5cf4f1fdebdaa4fe96c878d65b34ac4f685fd93c8a","sha256:cb540e5efc308da2f2792191f0f4749ca9292fb4de2621eec22e3e637f3812ba"],"state_sha256":"ac2de9556541f089fd70aa134e1b70125d45d09e06a00365d1dd1f8ebda77cbe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GdsAxbJ1gkIDvRP6liZ/veyfaS/lhq8dQgVVTNALH175DCgIRr/Ccs6Bm8rgCQDVo4VkufbB5LKgiNykgtnzAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:16:53.240908Z","bundle_sha256":"939fc360d3c7ff8c3f4935a221498d98256f323c5a1113a1f291530091ab1baa"}}