{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:C2CYTODYFM3CDDFPAWYUEOD66M","short_pith_number":"pith:C2CYTODY","canonical_record":{"source":{"id":"2006.07314","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T16:52:29Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"179b208d28eeb238214a1207e10cac696c95bffdfab7ab0618d26beab74403a7","abstract_canon_sha256":"d2bb0f7066e1fdc91b1b0c0b76221bd9aee270264b7db9bb1abe24935448a7ce"},"schema_version":"1.0"},"canonical_sha256":"168589b8782b36218caf05b142387ef33a701c8560623802f6672c82934c5db3","source":{"kind":"arxiv","id":"2006.07314","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07314","created_at":"2026-07-05T01:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07314v2","created_at":"2026-07-05T01:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07314","created_at":"2026-07-05T01:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"C2CYTODYFM3C","created_at":"2026-07-05T01:18:03Z"},{"alias_kind":"pith_short_16","alias_value":"C2CYTODYFM3CDDFP","created_at":"2026-07-05T01:18:03Z"},{"alias_kind":"pith_short_8","alias_value":"C2CYTODY","created_at":"2026-07-05T01:18:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:C2CYTODYFM3CDDFPAWYUEOD66M","target":"record","payload":{"canonical_record":{"source":{"id":"2006.07314","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T16:52:29Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"179b208d28eeb238214a1207e10cac696c95bffdfab7ab0618d26beab74403a7","abstract_canon_sha256":"d2bb0f7066e1fdc91b1b0c0b76221bd9aee270264b7db9bb1abe24935448a7ce"},"schema_version":"1.0"},"canonical_sha256":"168589b8782b36218caf05b142387ef33a701c8560623802f6672c82934c5db3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:03.539098Z","signature_b64":"2ErS8PXpPlTAu2zptUKdFv6kEvMBrgAd/bmUCtRB9Q4aoocgHpaDOi1jlpuui3dhJXkq0CSxqtgabtdO72CHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"168589b8782b36218caf05b142387ef33a701c8560623802f6672c82934c5db3","last_reissued_at":"2026-07-05T01:18:03.538654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:03.538654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.07314","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:18:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"58J3tkBpVpmUWENHx1OHUQCotVeUpM6hv27TJe75L3JHt4ridzvgx+BRlFNn5HMWztmqFLPsdJsOnL3j2Uk0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T13:27:39.733379Z"},"content_sha256":"d904d35be130c07fa1070d499bc35ef98e4daa7068bcfc657c9e707418de8500","schema_version":"1.0","event_id":"sha256:d904d35be130c07fa1070d499bc35ef98e4daa7068bcfc657c9e707418de8500"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:C2CYTODYFM3CDDFPAWYUEOD66M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zeroth-order Deterministic Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alejandro Ribeiro, Dionysios S. Kalogerias, George J. Pappas, Harshat Kumar","submitted_at":"2020-06-12T16:52:29Z","abstract_excerpt":"Deterministic Policy Gradient (DPG) removes a level of randomness from standard randomized-action Policy Gradient (PG), and demonstrates substantial empirical success for tackling complex dynamic problems involving Markov decision processes. At the same time, though, DPG loses its ability to learn in a model-free (i.e., actor-only) fashion, frequently necessitating the use of critics in order to obtain consistent estimates of the associated policy-reward gradient. In this work, we introduce Zeroth-order Deterministic Policy Gradient (ZDPG), which approximates policy-reward gradients via two-po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07314","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.07314/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:18:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dVhd+DCS4i4ETx8jyfScy4VQQHCTBGyi0Ak0nwRJLeDSq14x9YQkjjg1IJAhjhvZ8UCVIIksXA2TYSVGQMb6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T13:27:39.734054Z"},"content_sha256":"b624ce3c75c351d00fe8f6e18f4b5658352e28f299fb05d53c4703269cf1fbc0","schema_version":"1.0","event_id":"sha256:b624ce3c75c351d00fe8f6e18f4b5658352e28f299fb05d53c4703269cf1fbc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C2CYTODYFM3CDDFPAWYUEOD66M/bundle.json","state_url":"https://pith.science/pith/C2CYTODYFM3CDDFPAWYUEOD66M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C2CYTODYFM3CDDFPAWYUEOD66M/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":"2026-08-23T13:27:39Z","links":{"resolver":"https://pith.science/pith/C2CYTODYFM3CDDFPAWYUEOD66M","bundle":"https://pith.science/pith/C2CYTODYFM3CDDFPAWYUEOD66M/bundle.json","state":"https://pith.science/pith/C2CYTODYFM3CDDFPAWYUEOD66M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C2CYTODYFM3CDDFPAWYUEOD66M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:C2CYTODYFM3CDDFPAWYUEOD66M","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":"d2bb0f7066e1fdc91b1b0c0b76221bd9aee270264b7db9bb1abe24935448a7ce","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T16:52:29Z","title_canon_sha256":"179b208d28eeb238214a1207e10cac696c95bffdfab7ab0618d26beab74403a7"},"schema_version":"1.0","source":{"id":"2006.07314","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07314","created_at":"2026-07-05T01:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07314v2","created_at":"2026-07-05T01:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07314","created_at":"2026-07-05T01:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"C2CYTODYFM3C","created_at":"2026-07-05T01:18:03Z"},{"alias_kind":"pith_short_16","alias_value":"C2CYTODYFM3CDDFP","created_at":"2026-07-05T01:18:03Z"},{"alias_kind":"pith_short_8","alias_value":"C2CYTODY","created_at":"2026-07-05T01:18:03Z"}],"graph_snapshots":[{"event_id":"sha256:b624ce3c75c351d00fe8f6e18f4b5658352e28f299fb05d53c4703269cf1fbc0","target":"graph","created_at":"2026-07-05T01:18:03Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.07314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deterministic Policy Gradient (DPG) removes a level of randomness from standard randomized-action Policy Gradient (PG), and demonstrates substantial empirical success for tackling complex dynamic problems involving Markov decision processes. At the same time, though, DPG loses its ability to learn in a model-free (i.e., actor-only) fashion, frequently necessitating the use of critics in order to obtain consistent estimates of the associated policy-reward gradient. In this work, we introduce Zeroth-order Deterministic Policy Gradient (ZDPG), which approximates policy-reward gradients via two-po","authors_text":"Alejandro Ribeiro, Dionysios S. Kalogerias, George J. Pappas, Harshat Kumar","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T16:52:29Z","title":"Zeroth-order Deterministic Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07314","kind":"arxiv","version":2},"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:d904d35be130c07fa1070d499bc35ef98e4daa7068bcfc657c9e707418de8500","target":"record","created_at":"2026-07-05T01:18:03Z","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":"d2bb0f7066e1fdc91b1b0c0b76221bd9aee270264b7db9bb1abe24935448a7ce","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T16:52:29Z","title_canon_sha256":"179b208d28eeb238214a1207e10cac696c95bffdfab7ab0618d26beab74403a7"},"schema_version":"1.0","source":{"id":"2006.07314","kind":"arxiv","version":2}},"canonical_sha256":"168589b8782b36218caf05b142387ef33a701c8560623802f6672c82934c5db3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"168589b8782b36218caf05b142387ef33a701c8560623802f6672c82934c5db3","first_computed_at":"2026-07-05T01:18:03.538654Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:18:03.538654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2ErS8PXpPlTAu2zptUKdFv6kEvMBrgAd/bmUCtRB9Q4aoocgHpaDOi1jlpuui3dhJXkq0CSxqtgabtdO72CHBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:18:03.539098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.07314","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d904d35be130c07fa1070d499bc35ef98e4daa7068bcfc657c9e707418de8500","sha256:b624ce3c75c351d00fe8f6e18f4b5658352e28f299fb05d53c4703269cf1fbc0"],"state_sha256":"5b818e9d28b34a59f3eb6bb00705e251423e631f2f53cbb3613e53faaae369c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u36DUntisCBIg+g330W8OsqIABy7hpWfrnQ52qjrc6uZH/CZtocAfK6V1n7HeaHZneNptevszA2V0TfRF0IMDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T13:27:39.739448Z","bundle_sha256":"f2f771993c2ae2c3499a4fa048ae65ec2fcefa1a1813d2e4dc63f62d8faaa279"}}