{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TOBLSCFQE664V3XSSBOCBQG4Y4","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":"0a40ef2def84c3088836b6b40d1fad8b62ced03276cae824ef9bbd738f2cd2df","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-09T15:03:18Z","title_canon_sha256":"0da9b34fd39aa476446aaa760365158fffd5f5a73510849075c752b9b810d4e7"},"schema_version":"1.0","source":{"id":"1903.03812","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.03812","created_at":"2026-05-17T23:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"1903.03812v3","created_at":"2026-05-17T23:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03812","created_at":"2026-05-17T23:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"TOBLSCFQE664","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TOBLSCFQE664V3XS","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TOBLSCFQ","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:a07ccf8a0fce6c917b0f646958df0bdb5098a79f94e1559b28b030581e7489d8","target":"graph","created_at":"2026-05-17T23:43:24Z","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"},"paper":{"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 ","authors_text":"Chandramouli Kamanchi, Raghuram Bharadwaj Diddigi, Shalabh Bhatnagar","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-09T15:03:18Z","title":"Successive Over Relaxation Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03812","kind":"arxiv","version":3},"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:d21a8e9428392e0eb1a0d8eb25bc5a2050c595d6803f04586fd6c5bc25d4b4cd","target":"record","created_at":"2026-05-17T23:43:24Z","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":"0a40ef2def84c3088836b6b40d1fad8b62ced03276cae824ef9bbd738f2cd2df","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-09T15:03:18Z","title_canon_sha256":"0da9b34fd39aa476446aaa760365158fffd5f5a73510849075c752b9b810d4e7"},"schema_version":"1.0","source":{"id":"1903.03812","kind":"arxiv","version":3}},"canonical_sha256":"9b82b908b027bdcaeef2905c20c0dcc72125ac9237f20310dc3cfbc7e0111e83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b82b908b027bdcaeef2905c20c0dcc72125ac9237f20310dc3cfbc7e0111e83","first_computed_at":"2026-05-17T23:43:24.212673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:24.212673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1H443JWTOTLOQyrZXz1C3Hl2xD2IxkVuoFf41V2vLJLysZXRC8yx0lAGt6OnsjZ3yfQGTz5La0VYCgLAvMm5Dw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:24.213369Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.03812","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d21a8e9428392e0eb1a0d8eb25bc5a2050c595d6803f04586fd6c5bc25d4b4cd","sha256:a07ccf8a0fce6c917b0f646958df0bdb5098a79f94e1559b28b030581e7489d8"],"state_sha256":"6894238c252dd9d7aa54964e0dfdffad899493f8dfbb7ffaa08d8cde5d8a7502"}