{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:FF53VE7JVNE744EASANCHQTMEE","short_pith_number":"pith:FF53VE7J","canonical_record":{"source":{"id":"1403.4179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-03-17T17:26:57Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"83061a0ec0a002437a710df04a3b91ebcd2983857f45eea8280d7f606ba30f5e","abstract_canon_sha256":"addeb574f820c1c5d8a850cb1452305a2864f4c7962012077da7f2506bcc4241"},"schema_version":"1.0"},"canonical_sha256":"297bba93e9ab49fe7080901a23c26c212b14332b8d20656c465b1219908bd1fe","source":{"kind":"arxiv","id":"1403.4179","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1403.4179","created_at":"2026-05-18T02:56:12Z"},{"alias_kind":"arxiv_version","alias_value":"1403.4179v1","created_at":"2026-05-18T02:56:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.4179","created_at":"2026-05-18T02:56:12Z"},{"alias_kind":"pith_short_12","alias_value":"FF53VE7JVNE7","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FF53VE7JVNE744EA","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FF53VE7J","created_at":"2026-05-18T12:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:FF53VE7JVNE744EASANCHQTMEE","target":"record","payload":{"canonical_record":{"source":{"id":"1403.4179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-03-17T17:26:57Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"83061a0ec0a002437a710df04a3b91ebcd2983857f45eea8280d7f606ba30f5e","abstract_canon_sha256":"addeb574f820c1c5d8a850cb1452305a2864f4c7962012077da7f2506bcc4241"},"schema_version":"1.0"},"canonical_sha256":"297bba93e9ab49fe7080901a23c26c212b14332b8d20656c465b1219908bd1fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:56:12.050421Z","signature_b64":"hqpbHYmDXVG1lRwXtaQrlxFVBIS/hkdAGp70Oa0b2L9oZnfAuh9c6/kIsNnrCJEaizi1p9xAm3DQcqvZE7NSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"297bba93e9ab49fe7080901a23c26c212b14332b8d20656c465b1219908bd1fe","last_reissued_at":"2026-05-18T02:56:12.050064Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:56:12.050064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1403.4179","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:56:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"INk+klH/3r4xeJSgaYPzvPEW9Wpi3b9IRe1grX4+Zsm1SQr4QaUBI4z9dALpd17A27JOGs6x3uymPagcHZ06Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T16:35:16.681714Z"},"content_sha256":"9311c16ed343e81026559def459ef4c273c13d453636c350a57d3f8986faf22d","schema_version":"1.0","event_id":"sha256:9311c16ed343e81026559def459ef4c273c13d453636c350a57d3f8986faf22d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:FF53VE7JVNE744EASANCHQTMEE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximate dynamic programming with $(\\min,+)$ linear function approximation for Markov decision processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.SY","authors_text":"Chandrashekar Lakshminarayanan, Shalabh Bhatnagar","submitted_at":"2014-03-17T17:26:57Z","abstract_excerpt":"Markov Decision Processes (MDP) is an useful framework to cast optimal sequential decision making problems. Given any MDP the aim is to find the optimal action selection mechanism i.e., the optimal policy. Typically, the optimal policy ($u^*$) is obtained by substituting the optimal value-function ($J^*$) in the Bellman equation. Alternately $u^*$ is also obtained by learning the optimal state-action value function $Q^*$ known as the $Q$ value-function. However, it is difficult to compute the exact values of $J^*$ or $Q^*$ for MDPs with large number of states. Approximate Dynamic Programming ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.4179","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:56:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AtXF37uon0QYLkwWbDaiYRy9eCwxMWlOaRZZFW06Dvtbl/ta8RTiDxncuImmtdf0bTZBFB7OtFiJ2H8gDw74CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T16:35:16.682052Z"},"content_sha256":"3f72ab601eaab8182b04feced7c66e251896a8bf389ae24aa36f9e2e2168baaf","schema_version":"1.0","event_id":"sha256:3f72ab601eaab8182b04feced7c66e251896a8bf389ae24aa36f9e2e2168baaf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FF53VE7JVNE744EASANCHQTMEE/bundle.json","state_url":"https://pith.science/pith/FF53VE7JVNE744EASANCHQTMEE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FF53VE7JVNE744EASANCHQTMEE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T16:35:16Z","links":{"resolver":"https://pith.science/pith/FF53VE7JVNE744EASANCHQTMEE","bundle":"https://pith.science/pith/FF53VE7JVNE744EASANCHQTMEE/bundle.json","state":"https://pith.science/pith/FF53VE7JVNE744EASANCHQTMEE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FF53VE7JVNE744EASANCHQTMEE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:FF53VE7JVNE744EASANCHQTMEE","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":"addeb574f820c1c5d8a850cb1452305a2864f4c7962012077da7f2506bcc4241","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-03-17T17:26:57Z","title_canon_sha256":"83061a0ec0a002437a710df04a3b91ebcd2983857f45eea8280d7f606ba30f5e"},"schema_version":"1.0","source":{"id":"1403.4179","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1403.4179","created_at":"2026-05-18T02:56:12Z"},{"alias_kind":"arxiv_version","alias_value":"1403.4179v1","created_at":"2026-05-18T02:56:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.4179","created_at":"2026-05-18T02:56:12Z"},{"alias_kind":"pith_short_12","alias_value":"FF53VE7JVNE7","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FF53VE7JVNE744EA","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FF53VE7J","created_at":"2026-05-18T12:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:3f72ab601eaab8182b04feced7c66e251896a8bf389ae24aa36f9e2e2168baaf","target":"graph","created_at":"2026-05-18T02:56:12Z","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":"Markov Decision Processes (MDP) is an useful framework to cast optimal sequential decision making problems. Given any MDP the aim is to find the optimal action selection mechanism i.e., the optimal policy. Typically, the optimal policy ($u^*$) is obtained by substituting the optimal value-function ($J^*$) in the Bellman equation. Alternately $u^*$ is also obtained by learning the optimal state-action value function $Q^*$ known as the $Q$ value-function. However, it is difficult to compute the exact values of $J^*$ or $Q^*$ for MDPs with large number of states. Approximate Dynamic Programming (","authors_text":"Chandrashekar Lakshminarayanan, Shalabh Bhatnagar","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-03-17T17:26:57Z","title":"Approximate dynamic programming with $(\\min,+)$ linear function approximation for Markov decision processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.4179","kind":"arxiv","version":1},"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":"sha256:9311c16ed343e81026559def459ef4c273c13d453636c350a57d3f8986faf22d","target":"record","created_at":"2026-05-18T02:56:12Z","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":"addeb574f820c1c5d8a850cb1452305a2864f4c7962012077da7f2506bcc4241","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-03-17T17:26:57Z","title_canon_sha256":"83061a0ec0a002437a710df04a3b91ebcd2983857f45eea8280d7f606ba30f5e"},"schema_version":"1.0","source":{"id":"1403.4179","kind":"arxiv","version":1}},"canonical_sha256":"297bba93e9ab49fe7080901a23c26c212b14332b8d20656c465b1219908bd1fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"297bba93e9ab49fe7080901a23c26c212b14332b8d20656c465b1219908bd1fe","first_computed_at":"2026-05-18T02:56:12.050064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:56:12.050064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hqpbHYmDXVG1lRwXtaQrlxFVBIS/hkdAGp70Oa0b2L9oZnfAuh9c6/kIsNnrCJEaizi1p9xAm3DQcqvZE7NSDw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:56:12.050421Z","signed_message":"canonical_sha256_bytes"},"source_id":"1403.4179","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9311c16ed343e81026559def459ef4c273c13d453636c350a57d3f8986faf22d","sha256:3f72ab601eaab8182b04feced7c66e251896a8bf389ae24aa36f9e2e2168baaf"],"state_sha256":"76c8f56b6cdffdc57e6901d8efaec2f7b32757c78047c7b10bf655436056d9ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aC9z+PouezpUbMZ9iwowWDyOt7o+ch+RatT6j0E4auINWFNTKR9L6B1MAQGSUyWKHB4r+yYWOobgFjp+NYBQCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T16:35:16.683891Z","bundle_sha256":"e794d82cf7b384c2115da7d33e10d68bcb2ab9c1ebf9ebbeaf63337b06e9aa88"}}