{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QB464C5HBNU2AAIGN63R2ORGMV","short_pith_number":"pith:QB464C5H","schema_version":"1.0","canonical_sha256":"8079ee0ba70b69a001066fb71d3a26656625104e3f7f2cfbc545efdc4e7e63f4","source":{"kind":"arxiv","id":"1910.00211","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Multi-Objective Optimization of Online Decisions in High-Dimensional Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Balaraman Ravindran, Hardik Meisheri, Harshad Khadilkar, Nazneen N Sultana, Vinita Baniwal","submitted_at":"2019-10-01T06:16:48Z","abstract_excerpt":"This paper describes a purely data-driven solution to a class of sequential decision-making problems with a large number of concurrent online decisions, with applications to computing systems and operations research. We assume that while the micro-level behaviour of the system can be broadly captured by analytical expressions or simulation, the macro-level or emergent behaviour is complicated by non-linearity, constraints, and stochasticity. If we represent the set of concurrent decisions to be computed as a vector, each element of the vector is assumed to be a continuous variable, and the num"},"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":"1910.00211","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-10-01T06:16:48Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"32e3e17950f5e961b7ecc75fa02eff1737522062e4b416f9294f06571360c5d6","abstract_canon_sha256":"bdf837088592e1d32ea7f2ea724fc9e329a07515f5b89cca7afe79709df299d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:08:43.758635Z","signature_b64":"s5Jej3hCP2ZEOxFxDXfXvWD2adHyvgNtwqwp9v2o7UzK9FuocH4z45KyOazaDmif6ON8yEjnqOIyRTKWBU/PBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8079ee0ba70b69a001066fb71d3a26656625104e3f7f2cfbc545efdc4e7e63f4","last_reissued_at":"2026-07-05T00:08:43.758245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:08:43.758245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Multi-Objective Optimization of Online Decisions in High-Dimensional Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Balaraman Ravindran, Hardik Meisheri, Harshad Khadilkar, Nazneen N Sultana, Vinita Baniwal","submitted_at":"2019-10-01T06:16:48Z","abstract_excerpt":"This paper describes a purely data-driven solution to a class of sequential decision-making problems with a large number of concurrent online decisions, with applications to computing systems and operations research. We assume that while the micro-level behaviour of the system can be broadly captured by analytical expressions or simulation, the macro-level or emergent behaviour is complicated by non-linearity, constraints, and stochasticity. If we represent the set of concurrent decisions to be computed as a vector, each element of the vector is assumed to be a continuous variable, and the num"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.00211","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/1910.00211/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":"1910.00211","created_at":"2026-07-05T00:08:43.758300+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.00211v1","created_at":"2026-07-05T00:08:43.758300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.00211","created_at":"2026-07-05T00:08:43.758300+00:00"},{"alias_kind":"pith_short_12","alias_value":"QB464C5HBNU2","created_at":"2026-07-05T00:08:43.758300+00:00"},{"alias_kind":"pith_short_16","alias_value":"QB464C5HBNU2AAIG","created_at":"2026-07-05T00:08:43.758300+00:00"},{"alias_kind":"pith_short_8","alias_value":"QB464C5H","created_at":"2026-07-05T00:08:43.758300+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/QB464C5HBNU2AAIGN63R2ORGMV","json":"https://pith.science/pith/QB464C5HBNU2AAIGN63R2ORGMV.json","graph_json":"https://pith.science/api/pith-number/QB464C5HBNU2AAIGN63R2ORGMV/graph.json","events_json":"https://pith.science/api/pith-number/QB464C5HBNU2AAIGN63R2ORGMV/events.json","paper":"https://pith.science/paper/QB464C5H"},"agent_actions":{"view_html":"https://pith.science/pith/QB464C5HBNU2AAIGN63R2ORGMV","download_json":"https://pith.science/pith/QB464C5HBNU2AAIGN63R2ORGMV.json","view_paper":"https://pith.science/paper/QB464C5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.00211&json=true","fetch_graph":"https://pith.science/api/pith-number/QB464C5HBNU2AAIGN63R2ORGMV/graph.json","fetch_events":"https://pith.science/api/pith-number/QB464C5HBNU2AAIGN63R2ORGMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QB464C5HBNU2AAIGN63R2ORGMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QB464C5HBNU2AAIGN63R2ORGMV/action/storage_attestation","attest_author":"https://pith.science/pith/QB464C5HBNU2AAIGN63R2ORGMV/action/author_attestation","sign_citation":"https://pith.science/pith/QB464C5HBNU2AAIGN63R2ORGMV/action/citation_signature","submit_replication":"https://pith.science/pith/QB464C5HBNU2AAIGN63R2ORGMV/action/replication_record"}},"created_at":"2026-07-05T00:08:43.758300+00:00","updated_at":"2026-07-05T00:08:43.758300+00:00"}