{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TOBLSCFQE664V3XSSBOCBQG4Y4","short_pith_number":"pith:TOBLSCFQ","schema_version":"1.0","canonical_sha256":"9b82b908b027bdcaeef2905c20c0dcc72125ac9237f20310dc3cfbc7e0111e83","source":{"kind":"arxiv","id":"1903.03812","version":3},"attestation_state":"computed","paper":{"title":"Successive Over Relaxation Q-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chandramouli Kamanchi, Raghuram Bharadwaj Diddigi, Shalabh Bhatnagar","submitted_at":"2019-03-09T15:03:18Z","abstract_excerpt":"In a discounted reward Markov Decision Process (MDP), the objective is to find the optimal value function, i.e., the value function corresponding to an optimal policy. This problem reduces to solving a functional equation known as the Bellman equation and a fixed point iteration scheme known as the value iteration is utilized to obtain the solution. In literature, a successive over-relaxation based value iteration scheme is proposed to speed-up the computation of the optimal value function. The speed-up is achieved by constructing a modified Bellman equation that ensures faster convergence to "},"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":"1903.03812","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-09T15:03:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0da9b34fd39aa476446aaa760365158fffd5f5a73510849075c752b9b810d4e7","abstract_canon_sha256":"0a40ef2def84c3088836b6b40d1fad8b62ced03276cae824ef9bbd738f2cd2df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:24.213369Z","signature_b64":"1H443JWTOTLOQyrZXz1C3Hl2xD2IxkVuoFf41V2vLJLysZXRC8yx0lAGt6OnsjZ3yfQGTz5La0VYCgLAvMm5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b82b908b027bdcaeef2905c20c0dcc72125ac9237f20310dc3cfbc7e0111e83","last_reissued_at":"2026-05-17T23:43:24.212673Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:24.212673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Successive Over Relaxation Q-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chandramouli Kamanchi, Raghuram Bharadwaj Diddigi, Shalabh Bhatnagar","submitted_at":"2019-03-09T15:03:18Z","abstract_excerpt":"In a discounted reward Markov Decision Process (MDP), the objective is to find the optimal value function, i.e., the value function corresponding to an optimal policy. This problem reduces to solving a functional equation known as the Bellman equation and a fixed point iteration scheme known as the value iteration is utilized to obtain the solution. In literature, a successive over-relaxation based value iteration scheme is proposed to speed-up the computation of the optimal value function. The speed-up is achieved by constructing a modified Bellman equation that ensures faster convergence to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03812","kind":"arxiv","version":3},"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":"1903.03812","created_at":"2026-05-17T23:43:24.212772+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.03812v3","created_at":"2026-05-17T23:43:24.212772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03812","created_at":"2026-05-17T23:43:24.212772+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOBLSCFQE664","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOBLSCFQE664V3XS","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOBLSCFQ","created_at":"2026-05-18T12:33:30.264802+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/TOBLSCFQE664V3XSSBOCBQG4Y4","json":"https://pith.science/pith/TOBLSCFQE664V3XSSBOCBQG4Y4.json","graph_json":"https://pith.science/api/pith-number/TOBLSCFQE664V3XSSBOCBQG4Y4/graph.json","events_json":"https://pith.science/api/pith-number/TOBLSCFQE664V3XSSBOCBQG4Y4/events.json","paper":"https://pith.science/paper/TOBLSCFQ"},"agent_actions":{"view_html":"https://pith.science/pith/TOBLSCFQE664V3XSSBOCBQG4Y4","download_json":"https://pith.science/pith/TOBLSCFQE664V3XSSBOCBQG4Y4.json","view_paper":"https://pith.science/paper/TOBLSCFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.03812&json=true","fetch_graph":"https://pith.science/api/pith-number/TOBLSCFQE664V3XSSBOCBQG4Y4/graph.json","fetch_events":"https://pith.science/api/pith-number/TOBLSCFQE664V3XSSBOCBQG4Y4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOBLSCFQE664V3XSSBOCBQG4Y4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOBLSCFQE664V3XSSBOCBQG4Y4/action/storage_attestation","attest_author":"https://pith.science/pith/TOBLSCFQE664V3XSSBOCBQG4Y4/action/author_attestation","sign_citation":"https://pith.science/pith/TOBLSCFQE664V3XSSBOCBQG4Y4/action/citation_signature","submit_replication":"https://pith.science/pith/TOBLSCFQE664V3XSSBOCBQG4Y4/action/replication_record"}},"created_at":"2026-05-17T23:43:24.212772+00:00","updated_at":"2026-05-17T23:43:24.212772+00:00"}