{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:XGTZEEKVNTQNKRJF5PSPDA33X3","short_pith_number":"pith:XGTZEEKV","schema_version":"1.0","canonical_sha256":"b9a79211556ce0d54525ebe4f1837bbed064581e3578ea2d56b7482c220a8c7d","source":{"kind":"arxiv","id":"1403.6530","version":2},"attestation_state":"computed","paper":{"title":"Variance-Constrained Actor-Critic Algorithms for Discounted and Average Reward MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mohammad Ghavamzadeh, Prashanth L.A.","submitted_at":"2014-03-25T23:00:50Z","abstract_excerpt":"In many sequential decision-making problems we may want to manage risk by minimizing some measure of variability in rewards in addition to maximizing a standard criterion. Variance related risk measures are among the most common risk-sensitive criteria in finance and operations research. However, optimizing many such criteria is known to be a hard problem. In this paper, we consider both discounted and average reward Markov decision processes. For each formulation, we first define a measure of variability for a policy, which in turn gives us a set of risk-sensitive criteria to optimize. For ea"},"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":"1403.6530","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-03-25T23:00:50Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"6570276323de258861d8b17ec064662225a2656ee88a2ba6739aa59a8a384385","abstract_canon_sha256":"fd09e054e0cc83fd12e2483701ea6d877bf8263cb9e637c91b7f1525a990e939"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:21:51.907974Z","signature_b64":"KXc/Bot7CfPvNKJUfJWM1c+RLflyLs8GKUpxn7XzdsZrIpbF+oytPyv2saAvs1ALW5Ca4lazylCaHNdMdgfUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9a79211556ce0d54525ebe4f1837bbed064581e3578ea2d56b7482c220a8c7d","last_reissued_at":"2026-05-18T02:21:51.907418Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:21:51.907418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variance-Constrained Actor-Critic Algorithms for Discounted and Average Reward MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mohammad Ghavamzadeh, Prashanth L.A.","submitted_at":"2014-03-25T23:00:50Z","abstract_excerpt":"In many sequential decision-making problems we may want to manage risk by minimizing some measure of variability in rewards in addition to maximizing a standard criterion. Variance related risk measures are among the most common risk-sensitive criteria in finance and operations research. However, optimizing many such criteria is known to be a hard problem. In this paper, we consider both discounted and average reward Markov decision processes. For each formulation, we first define a measure of variability for a policy, which in turn gives us a set of risk-sensitive criteria to optimize. For ea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.6530","kind":"arxiv","version":2},"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":"1403.6530","created_at":"2026-05-18T02:21:51.907506+00:00"},{"alias_kind":"arxiv_version","alias_value":"1403.6530v2","created_at":"2026-05-18T02:21:51.907506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.6530","created_at":"2026-05-18T02:21:51.907506+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGTZEEKVNTQN","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGTZEEKVNTQNKRJF","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGTZEEKV","created_at":"2026-05-18T12:28:57.508820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00654","citing_title":"Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XGTZEEKVNTQNKRJF5PSPDA33X3","json":"https://pith.science/pith/XGTZEEKVNTQNKRJF5PSPDA33X3.json","graph_json":"https://pith.science/api/pith-number/XGTZEEKVNTQNKRJF5PSPDA33X3/graph.json","events_json":"https://pith.science/api/pith-number/XGTZEEKVNTQNKRJF5PSPDA33X3/events.json","paper":"https://pith.science/paper/XGTZEEKV"},"agent_actions":{"view_html":"https://pith.science/pith/XGTZEEKVNTQNKRJF5PSPDA33X3","download_json":"https://pith.science/pith/XGTZEEKVNTQNKRJF5PSPDA33X3.json","view_paper":"https://pith.science/paper/XGTZEEKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1403.6530&json=true","fetch_graph":"https://pith.science/api/pith-number/XGTZEEKVNTQNKRJF5PSPDA33X3/graph.json","fetch_events":"https://pith.science/api/pith-number/XGTZEEKVNTQNKRJF5PSPDA33X3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGTZEEKVNTQNKRJF5PSPDA33X3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGTZEEKVNTQNKRJF5PSPDA33X3/action/storage_attestation","attest_author":"https://pith.science/pith/XGTZEEKVNTQNKRJF5PSPDA33X3/action/author_attestation","sign_citation":"https://pith.science/pith/XGTZEEKVNTQNKRJF5PSPDA33X3/action/citation_signature","submit_replication":"https://pith.science/pith/XGTZEEKVNTQNKRJF5PSPDA33X3/action/replication_record"}},"created_at":"2026-05-18T02:21:51.907506+00:00","updated_at":"2026-05-18T02:21:51.907506+00:00"}