{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:NIIFSJFQHF4WIZ7N5HM33RD6B2","short_pith_number":"pith:NIIFSJFQ","canonical_record":{"source":{"id":"1311.5918","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2013-11-22T22:12:29Z","cross_cats_sorted":[],"title_canon_sha256":"c736622650ccecac7ff29ffd4411e6d8bffa9774ab4ed4191fb92f872726ccc7","abstract_canon_sha256":"209c635bd8b37b5fa1d1d463a2d101145cb25657c0e985502ba8c6fa412b13b6"},"schema_version":"1.0"},"canonical_sha256":"6a105924b039796467ede9d9bdc47e0e8e1fafda14adc76bc3f6b0cefe2e129f","source":{"kind":"arxiv","id":"1311.5918","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1311.5918","created_at":"2026-05-18T03:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"1311.5918v1","created_at":"2026-05-18T03:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.5918","created_at":"2026-05-18T03:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"NIIFSJFQHF4W","created_at":"2026-05-18T12:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"NIIFSJFQHF4WIZ7N","created_at":"2026-05-18T12:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"NIIFSJFQ","created_at":"2026-05-18T12:27:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:NIIFSJFQHF4WIZ7N5HM33RD6B2","target":"record","payload":{"canonical_record":{"source":{"id":"1311.5918","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2013-11-22T22:12:29Z","cross_cats_sorted":[],"title_canon_sha256":"c736622650ccecac7ff29ffd4411e6d8bffa9774ab4ed4191fb92f872726ccc7","abstract_canon_sha256":"209c635bd8b37b5fa1d1d463a2d101145cb25657c0e985502ba8c6fa412b13b6"},"schema_version":"1.0"},"canonical_sha256":"6a105924b039796467ede9d9bdc47e0e8e1fafda14adc76bc3f6b0cefe2e129f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:06:21.113559Z","signature_b64":"5eNgraukmqDlczFvhpArAFHR5CtCynpGAWopMUsnUTT8TBA5zWSWctmRBbd5F8zSHNELjKDWmljVouUR+AHgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a105924b039796467ede9d9bdc47e0e8e1fafda14adc76bc3f6b0cefe2e129f","last_reissued_at":"2026-05-18T03:06:21.113017Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:06:21.113017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1311.5918","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":"2026-05-18T03:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T12s38lOILPnZ3NFVgocZxcmEEkYqGGwkvBYO8qwTPolo+buskzGGtUJTrBWufVN0ocp9ZBid22JbU7RCYpjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:24:50.880949Z"},"content_sha256":"2d6a892db8684a78ec080336537ad444ed48f503bccf50051154b5f9834db258","schema_version":"1.0","event_id":"sha256:2d6a892db8684a78ec080336537ad444ed48f503bccf50051154b5f9834db258"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:NIIFSJFQHF4WIZ7N5HM33RD6B2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Empirical Dynamic Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Dileep Kalathil, Rahul Jain, William B. Haskell","submitted_at":"2013-11-22T22:12:29Z","abstract_excerpt":"We propose empirical dynamic programming algorithms for Markov decision processes (MDPs). In these algorithms, the exact expectation in the Bellman operator in classical value iteration is replaced by an empirical estimate to get `empirical value iteration' (EVI). Policy evaluation and policy improvement in classical policy iteration are also replaced by simulation to get `empirical policy iteration' (EPI). Thus, these empirical dynamic programming algorithms involve iteration of a random operator, the empirical Bellman operator. We introduce notions of probabilistic fixed points for such rand"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.5918","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":"2026-05-18T03:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OZHyJepoxIT0E5JxUfRdMMHQh4b6KWKyKiFW12sR0Hhip+ITma9H7JA8us/CA/fSutLjzN5p/2lS0dMgSFcjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T07:24:50.881657Z"},"content_sha256":"1fe8139270bfef636514f6c8a92b4bdb57435bd1563332d0ea6bd7309d491d96","schema_version":"1.0","event_id":"sha256:1fe8139270bfef636514f6c8a92b4bdb57435bd1563332d0ea6bd7309d491d96"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NIIFSJFQHF4WIZ7N5HM33RD6B2/bundle.json","state_url":"https://pith.science/pith/NIIFSJFQHF4WIZ7N5HM33RD6B2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NIIFSJFQHF4WIZ7N5HM33RD6B2/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":"2026-05-26T07:24:50Z","links":{"resolver":"https://pith.science/pith/NIIFSJFQHF4WIZ7N5HM33RD6B2","bundle":"https://pith.science/pith/NIIFSJFQHF4WIZ7N5HM33RD6B2/bundle.json","state":"https://pith.science/pith/NIIFSJFQHF4WIZ7N5HM33RD6B2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NIIFSJFQHF4WIZ7N5HM33RD6B2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:NIIFSJFQHF4WIZ7N5HM33RD6B2","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":"209c635bd8b37b5fa1d1d463a2d101145cb25657c0e985502ba8c6fa412b13b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2013-11-22T22:12:29Z","title_canon_sha256":"c736622650ccecac7ff29ffd4411e6d8bffa9774ab4ed4191fb92f872726ccc7"},"schema_version":"1.0","source":{"id":"1311.5918","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1311.5918","created_at":"2026-05-18T03:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"1311.5918v1","created_at":"2026-05-18T03:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.5918","created_at":"2026-05-18T03:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"NIIFSJFQHF4W","created_at":"2026-05-18T12:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"NIIFSJFQHF4WIZ7N","created_at":"2026-05-18T12:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"NIIFSJFQ","created_at":"2026-05-18T12:27:52Z"}],"graph_snapshots":[{"event_id":"sha256:1fe8139270bfef636514f6c8a92b4bdb57435bd1563332d0ea6bd7309d491d96","target":"graph","created_at":"2026-05-18T03:06:21Z","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":"We propose empirical dynamic programming algorithms for Markov decision processes (MDPs). In these algorithms, the exact expectation in the Bellman operator in classical value iteration is replaced by an empirical estimate to get `empirical value iteration' (EVI). Policy evaluation and policy improvement in classical policy iteration are also replaced by simulation to get `empirical policy iteration' (EPI). Thus, these empirical dynamic programming algorithms involve iteration of a random operator, the empirical Bellman operator. We introduce notions of probabilistic fixed points for such rand","authors_text":"Dileep Kalathil, Rahul Jain, William B. Haskell","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2013-11-22T22:12:29Z","title":"Empirical Dynamic Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.5918","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":"sha256:2d6a892db8684a78ec080336537ad444ed48f503bccf50051154b5f9834db258","target":"record","created_at":"2026-05-18T03:06:21Z","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":"209c635bd8b37b5fa1d1d463a2d101145cb25657c0e985502ba8c6fa412b13b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2013-11-22T22:12:29Z","title_canon_sha256":"c736622650ccecac7ff29ffd4411e6d8bffa9774ab4ed4191fb92f872726ccc7"},"schema_version":"1.0","source":{"id":"1311.5918","kind":"arxiv","version":1}},"canonical_sha256":"6a105924b039796467ede9d9bdc47e0e8e1fafda14adc76bc3f6b0cefe2e129f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a105924b039796467ede9d9bdc47e0e8e1fafda14adc76bc3f6b0cefe2e129f","first_computed_at":"2026-05-18T03:06:21.113017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:06:21.113017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5eNgraukmqDlczFvhpArAFHR5CtCynpGAWopMUsnUTT8TBA5zWSWctmRBbd5F8zSHNELjKDWmljVouUR+AHgBw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:06:21.113559Z","signed_message":"canonical_sha256_bytes"},"source_id":"1311.5918","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d6a892db8684a78ec080336537ad444ed48f503bccf50051154b5f9834db258","sha256:1fe8139270bfef636514f6c8a92b4bdb57435bd1563332d0ea6bd7309d491d96"],"state_sha256":"ac0ba2edd692b6e5860f7b9a2e1664ffbd14d39fb0ac5406b5718a55bc2a913d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8TgI9knDhZ6qOnC31FD8IVV/0DoSW/WjR2Cpt3Ln+NTQ/9K6G/P25cA1IrU7CbAWXWWsU/Qp6l75LgVRp0FMAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T07:24:50.885027Z","bundle_sha256":"f452be19cf6db91e969ac2ab12fa46446de435ab737c0a69958291c267c3196e"}}