{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SDIIOWFSTIPKZLG5L3VB7656YD","short_pith_number":"pith:SDIIOWFS","schema_version":"1.0","canonical_sha256":"90d08758b29a1eacacdd5eea1ffbbec0e4a66baba62a0b52935e6276931ae171","source":{"kind":"arxiv","id":"1905.06466","version":1},"attestation_state":"computed","paper":{"title":"Exploration-Exploitation Trade-off in Reinforcement Learning on Online Markov Decision Processes with Global Concave Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Wang Chi Cheung","submitted_at":"2019-05-15T23:09:05Z","abstract_excerpt":"We consider an agent who is involved in a Markov decision process and receives a vector of outcomes every round. Her objective is to maximize a global concave reward function on the average vectorial outcome. The problem models applications such as multi-objective optimization, maximum entropy exploration, and constrained optimization in Markovian environments. In our general setting where a stationary policy could have multiple recurrent classes, the agent faces a subtle yet consequential trade-off in alternating among different actions for balancing the vectorial outcomes. In particular, sta"},"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":"1905.06466","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T23:09:05Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"0cacf4caef645469dc1ddb04a08f9e9cb668657d599819f853d6d6cfdc5b504b","abstract_canon_sha256":"a6da5c418229e18020adecfe7cd8b19a5f0f8f81df096a6d25ca036ffe08ba57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:02.282582Z","signature_b64":"3Sj88ba2g+aKcErXhSIsJTaV2OCSF+KurUNAjh+SnivXErgmzFOhYZ1FKdd71wHgmN/TdhcwvJVLDFCfSN+GBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90d08758b29a1eacacdd5eea1ffbbec0e4a66baba62a0b52935e6276931ae171","last_reissued_at":"2026-05-17T23:46:02.281976Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:02.281976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploration-Exploitation Trade-off in Reinforcement Learning on Online Markov Decision Processes with Global Concave Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Wang Chi Cheung","submitted_at":"2019-05-15T23:09:05Z","abstract_excerpt":"We consider an agent who is involved in a Markov decision process and receives a vector of outcomes every round. Her objective is to maximize a global concave reward function on the average vectorial outcome. The problem models applications such as multi-objective optimization, maximum entropy exploration, and constrained optimization in Markovian environments. In our general setting where a stationary policy could have multiple recurrent classes, the agent faces a subtle yet consequential trade-off in alternating among different actions for balancing the vectorial outcomes. In particular, sta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06466","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":""},"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":"1905.06466","created_at":"2026-05-17T23:46:02.282094+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.06466v1","created_at":"2026-05-17T23:46:02.282094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06466","created_at":"2026-05-17T23:46:02.282094+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDIIOWFSTIPK","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDIIOWFSTIPKZLG5","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDIIOWFS","created_at":"2026-05-18T12:33:27.125529+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/SDIIOWFSTIPKZLG5L3VB7656YD","json":"https://pith.science/pith/SDIIOWFSTIPKZLG5L3VB7656YD.json","graph_json":"https://pith.science/api/pith-number/SDIIOWFSTIPKZLG5L3VB7656YD/graph.json","events_json":"https://pith.science/api/pith-number/SDIIOWFSTIPKZLG5L3VB7656YD/events.json","paper":"https://pith.science/paper/SDIIOWFS"},"agent_actions":{"view_html":"https://pith.science/pith/SDIIOWFSTIPKZLG5L3VB7656YD","download_json":"https://pith.science/pith/SDIIOWFSTIPKZLG5L3VB7656YD.json","view_paper":"https://pith.science/paper/SDIIOWFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.06466&json=true","fetch_graph":"https://pith.science/api/pith-number/SDIIOWFSTIPKZLG5L3VB7656YD/graph.json","fetch_events":"https://pith.science/api/pith-number/SDIIOWFSTIPKZLG5L3VB7656YD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDIIOWFSTIPKZLG5L3VB7656YD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDIIOWFSTIPKZLG5L3VB7656YD/action/storage_attestation","attest_author":"https://pith.science/pith/SDIIOWFSTIPKZLG5L3VB7656YD/action/author_attestation","sign_citation":"https://pith.science/pith/SDIIOWFSTIPKZLG5L3VB7656YD/action/citation_signature","submit_replication":"https://pith.science/pith/SDIIOWFSTIPKZLG5L3VB7656YD/action/replication_record"}},"created_at":"2026-05-17T23:46:02.282094+00:00","updated_at":"2026-05-17T23:46:02.282094+00:00"}