{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JDG2HB5XYW7EYUWRRYRXXU4U7M","short_pith_number":"pith:JDG2HB5X","canonical_record":{"source":{"id":"1807.03708","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-10T15:24:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7e3b81cca0819874c3c47e74086cc85ab7beeef85480a1a127844c0fb009db00","abstract_canon_sha256":"8c1458c8ed4007c4ff10ec8a7f86fa0af77a171d105577b410f0333c9ba5f0ed"},"schema_version":"1.0"},"canonical_sha256":"48cda387b7c5be4c52d18e237bd394fb256d60ff58361b4910274e2da1fc41e4","source":{"kind":"arxiv","id":"1807.03708","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.03708","created_at":"2026-05-18T00:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"1807.03708v3","created_at":"2026-05-18T00:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03708","created_at":"2026-05-18T00:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"JDG2HB5XYW7E","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JDG2HB5XYW7EYUWR","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JDG2HB5X","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JDG2HB5XYW7EYUWRRYRXXU4U7M","target":"record","payload":{"canonical_record":{"source":{"id":"1807.03708","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-10T15:24:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7e3b81cca0819874c3c47e74086cc85ab7beeef85480a1a127844c0fb009db00","abstract_canon_sha256":"8c1458c8ed4007c4ff10ec8a7f86fa0af77a171d105577b410f0333c9ba5f0ed"},"schema_version":"1.0"},"canonical_sha256":"48cda387b7c5be4c52d18e237bd394fb256d60ff58361b4910274e2da1fc41e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:22.536752Z","signature_b64":"2f2lqOzSILsbmkjsMX5vpbdDBAeSAMVXHgpn5DS54Xml9R0dRzFLobYMmbON9lpldjLl1OA1cOXCLvM0h4BaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48cda387b7c5be4c52d18e237bd394fb256d60ff58361b4910274e2da1fc41e4","last_reissued_at":"2026-05-18T00:04:22.536004Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:22.536004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.03708","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b5dNS99CVq6L2ZJg6ULOFbVKJvPvjvrrWRxjZ/eai24wOyvsK4NqnwIHQltRUpDuRfgcjdh0ybOPv1yWukXZDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:38:36.239184Z"},"content_sha256":"d1af4c7b2a64c73e29548cad48e5406e456fe86e4a0bff402b8af64b26f197bb","schema_version":"1.0","event_id":"sha256:d1af4c7b2a64c73e29548cad48e5406e456fe86e4a0bff402b8af64b26f197bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JDG2HB5XYW7EYUWRRYRXXU4U7M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deterministic Policy Gradients With General State Transitions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ling Pan, Pingzhong Tang, Qingpeng Cai","submitted_at":"2018-07-10T15:24:36Z","abstract_excerpt":"We study a reinforcement learning setting, where the state transition function is a convex combination of a stochastic continuous function and a deterministic function. Such a setting generalizes the widely-studied stochastic state transition setting, namely the setting of deterministic policy gradient (DPG).\n  We firstly give a simple example to illustrate that the deterministic policy gradient may be infinite under deterministic state transitions, and introduce a theoretical technique to prove the existence of the policy gradient in this generalized setting. Using this technique, we prove th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03708","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cr0ccyPMVMvDnvOJXm9H/5c0Kb54cTaiy7HpAo0Ove5fzYitBI68Qg6bPQUZH8ikzk2QtN0ofhgljhBvnD/XDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:38:36.239546Z"},"content_sha256":"02c49054854dd72c13eb3e84e68f48e70db7f95c0e858e8d5b22ca512bf63345","schema_version":"1.0","event_id":"sha256:02c49054854dd72c13eb3e84e68f48e70db7f95c0e858e8d5b22ca512bf63345"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M/bundle.json","state_url":"https://pith.science/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M/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":"2026-06-01T20:38:36Z","links":{"resolver":"https://pith.science/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M","bundle":"https://pith.science/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M/bundle.json","state":"https://pith.science/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JDG2HB5XYW7EYUWRRYRXXU4U7M","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":"8c1458c8ed4007c4ff10ec8a7f86fa0af77a171d105577b410f0333c9ba5f0ed","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-10T15:24:36Z","title_canon_sha256":"7e3b81cca0819874c3c47e74086cc85ab7beeef85480a1a127844c0fb009db00"},"schema_version":"1.0","source":{"id":"1807.03708","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.03708","created_at":"2026-05-18T00:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"1807.03708v3","created_at":"2026-05-18T00:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03708","created_at":"2026-05-18T00:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"JDG2HB5XYW7E","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JDG2HB5XYW7EYUWR","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JDG2HB5X","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:02c49054854dd72c13eb3e84e68f48e70db7f95c0e858e8d5b22ca512bf63345","target":"graph","created_at":"2026-05-18T00:04:22Z","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 study a reinforcement learning setting, where the state transition function is a convex combination of a stochastic continuous function and a deterministic function. Such a setting generalizes the widely-studied stochastic state transition setting, namely the setting of deterministic policy gradient (DPG).\n  We firstly give a simple example to illustrate that the deterministic policy gradient may be infinite under deterministic state transitions, and introduce a theoretical technique to prove the existence of the policy gradient in this generalized setting. Using this technique, we prove th","authors_text":"Ling Pan, Pingzhong Tang, Qingpeng Cai","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-10T15:24:36Z","title":"Deterministic Policy Gradients With General State Transitions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03708","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:d1af4c7b2a64c73e29548cad48e5406e456fe86e4a0bff402b8af64b26f197bb","target":"record","created_at":"2026-05-18T00:04:22Z","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":"8c1458c8ed4007c4ff10ec8a7f86fa0af77a171d105577b410f0333c9ba5f0ed","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-10T15:24:36Z","title_canon_sha256":"7e3b81cca0819874c3c47e74086cc85ab7beeef85480a1a127844c0fb009db00"},"schema_version":"1.0","source":{"id":"1807.03708","kind":"arxiv","version":3}},"canonical_sha256":"48cda387b7c5be4c52d18e237bd394fb256d60ff58361b4910274e2da1fc41e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48cda387b7c5be4c52d18e237bd394fb256d60ff58361b4910274e2da1fc41e4","first_computed_at":"2026-05-18T00:04:22.536004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:04:22.536004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2f2lqOzSILsbmkjsMX5vpbdDBAeSAMVXHgpn5DS54Xml9R0dRzFLobYMmbON9lpldjLl1OA1cOXCLvM0h4BaCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:04:22.536752Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.03708","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1af4c7b2a64c73e29548cad48e5406e456fe86e4a0bff402b8af64b26f197bb","sha256:02c49054854dd72c13eb3e84e68f48e70db7f95c0e858e8d5b22ca512bf63345"],"state_sha256":"10b2cadfba909b27a0c3cd4bbd2097d84adf78ba8ac8e59cb0d1b21a09ff9a48"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RpzBpUOTG0YaT5mBvyr4mO0lRDqI1dc6y4+Dk8JSo3WgHJKMmnvFhIuersrTT9LdERIIVxfDcUsi8dqQP5stCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T20:38:36.241508Z","bundle_sha256":"c8583d316698eb634ca0b2250adca1e58c4606cc84dc94e4f90782cc94507e15"}}