{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JDG2HB5XYW7EYUWRRYRXXU4U7M","short_pith_number":"pith:JDG2HB5X","schema_version":"1.0","canonical_sha256":"48cda387b7c5be4c52d18e237bd394fb256d60ff58361b4910274e2da1fc41e4","source":{"kind":"arxiv","id":"1807.03708","version":3},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1807.03708","created_at":"2026-05-18T00:04:22.536118+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.03708v3","created_at":"2026-05-18T00:04:22.536118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03708","created_at":"2026-05-18T00:04:22.536118+00:00"},{"alias_kind":"pith_short_12","alias_value":"JDG2HB5XYW7E","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JDG2HB5XYW7EYUWR","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JDG2HB5X","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M","json":"https://pith.science/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M.json","graph_json":"https://pith.science/api/pith-number/JDG2HB5XYW7EYUWRRYRXXU4U7M/graph.json","events_json":"https://pith.science/api/pith-number/JDG2HB5XYW7EYUWRRYRXXU4U7M/events.json","paper":"https://pith.science/paper/JDG2HB5X"},"agent_actions":{"view_html":"https://pith.science/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M","download_json":"https://pith.science/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M.json","view_paper":"https://pith.science/paper/JDG2HB5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.03708&json=true","fetch_graph":"https://pith.science/api/pith-number/JDG2HB5XYW7EYUWRRYRXXU4U7M/graph.json","fetch_events":"https://pith.science/api/pith-number/JDG2HB5XYW7EYUWRRYRXXU4U7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M/action/storage_attestation","attest_author":"https://pith.science/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M/action/author_attestation","sign_citation":"https://pith.science/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M/action/citation_signature","submit_replication":"https://pith.science/pith/JDG2HB5XYW7EYUWRRYRXXU4U7M/action/replication_record"}},"created_at":"2026-05-18T00:04:22.536118+00:00","updated_at":"2026-05-18T00:04:22.536118+00:00"}