{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:TPWSET5DPVEZGHWO6MHRWZG3SO","short_pith_number":"pith:TPWSET5D","schema_version":"1.0","canonical_sha256":"9bed224fa37d49931ecef30f1b64db93bc36c310cdbfdb245cf0e2caf292c3ef","source":{"kind":"arxiv","id":"1712.02467","version":1},"attestation_state":"computed","paper":{"title":"Deep Primal-Dual Reinforcement Learning: Accelerating Actor-Critic using Bellman Duality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mengdi Wang, Woon Sang Cho","submitted_at":"2017-12-07T01:41:51Z","abstract_excerpt":"We develop a parameterized Primal-Dual $\\pi$ Learning method based on deep neural networks for Markov decision process with large state space and off-policy reinforcement learning. In contrast to the popular Q-learning and actor-critic methods that are based on successive approximations to the nonlinear Bellman equation, our method makes primal-dual updates to the policy and value functions utilizing the fundamental linear Bellman duality. Naive parametrization of the primal-dual $\\pi$ learning method using deep neural networks would encounter two major challenges: (1) each update requires com"},"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":"1712.02467","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-07T01:41:51Z","cross_cats_sorted":[],"title_canon_sha256":"939a9bcefef8e959a06b9ef41ed3ff4e699d23f697074da7737830575854d13d","abstract_canon_sha256":"477d6389148794066ffc93972132bbfd5ca5a55e8f5f3f07604a54087c6f7f7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:34.046577Z","signature_b64":"lfuK9dJnYQbxH6EbU8RSZ+ES72je7/qICQE3SBfkSA0MzZXa8yCli6KDHqIo+IYuM6Et30Seqm4yxW01MFUfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bed224fa37d49931ecef30f1b64db93bc36c310cdbfdb245cf0e2caf292c3ef","last_reissued_at":"2026-05-18T00:28:34.045808Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:34.045808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Primal-Dual Reinforcement Learning: Accelerating Actor-Critic using Bellman Duality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mengdi Wang, Woon Sang Cho","submitted_at":"2017-12-07T01:41:51Z","abstract_excerpt":"We develop a parameterized Primal-Dual $\\pi$ Learning method based on deep neural networks for Markov decision process with large state space and off-policy reinforcement learning. In contrast to the popular Q-learning and actor-critic methods that are based on successive approximations to the nonlinear Bellman equation, our method makes primal-dual updates to the policy and value functions utilizing the fundamental linear Bellman duality. Naive parametrization of the primal-dual $\\pi$ learning method using deep neural networks would encounter two major challenges: (1) each update requires com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.02467","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1712.02467","created_at":"2026-05-18T00:28:34.045919+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.02467v1","created_at":"2026-05-18T00:28:34.045919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.02467","created_at":"2026-05-18T00:28:34.045919+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPWSET5DPVEZ","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPWSET5DPVEZGHWO","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPWSET5D","created_at":"2026-05-18T12:31:46.661854+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/TPWSET5DPVEZGHWO6MHRWZG3SO","json":"https://pith.science/pith/TPWSET5DPVEZGHWO6MHRWZG3SO.json","graph_json":"https://pith.science/api/pith-number/TPWSET5DPVEZGHWO6MHRWZG3SO/graph.json","events_json":"https://pith.science/api/pith-number/TPWSET5DPVEZGHWO6MHRWZG3SO/events.json","paper":"https://pith.science/paper/TPWSET5D"},"agent_actions":{"view_html":"https://pith.science/pith/TPWSET5DPVEZGHWO6MHRWZG3SO","download_json":"https://pith.science/pith/TPWSET5DPVEZGHWO6MHRWZG3SO.json","view_paper":"https://pith.science/paper/TPWSET5D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.02467&json=true","fetch_graph":"https://pith.science/api/pith-number/TPWSET5DPVEZGHWO6MHRWZG3SO/graph.json","fetch_events":"https://pith.science/api/pith-number/TPWSET5DPVEZGHWO6MHRWZG3SO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPWSET5DPVEZGHWO6MHRWZG3SO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPWSET5DPVEZGHWO6MHRWZG3SO/action/storage_attestation","attest_author":"https://pith.science/pith/TPWSET5DPVEZGHWO6MHRWZG3SO/action/author_attestation","sign_citation":"https://pith.science/pith/TPWSET5DPVEZGHWO6MHRWZG3SO/action/citation_signature","submit_replication":"https://pith.science/pith/TPWSET5DPVEZGHWO6MHRWZG3SO/action/replication_record"}},"created_at":"2026-05-18T00:28:34.045919+00:00","updated_at":"2026-05-18T00:28:34.045919+00:00"}