{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:TPWSET5DPVEZGHWO6MHRWZG3SO","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":"477d6389148794066ffc93972132bbfd5ca5a55e8f5f3f07604a54087c6f7f7c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-07T01:41:51Z","title_canon_sha256":"939a9bcefef8e959a06b9ef41ed3ff4e699d23f697074da7737830575854d13d"},"schema_version":"1.0","source":{"id":"1712.02467","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.02467","created_at":"2026-05-18T00:28:34Z"},{"alias_kind":"arxiv_version","alias_value":"1712.02467v1","created_at":"2026-05-18T00:28:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.02467","created_at":"2026-05-18T00:28:34Z"},{"alias_kind":"pith_short_12","alias_value":"TPWSET5DPVEZ","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"TPWSET5DPVEZGHWO","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"TPWSET5D","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:028c628d60a706c6805181ff7269b45f42a08c26fb9ba088b54b282315f6c047","target":"graph","created_at":"2026-05-18T00:28:34Z","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 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","authors_text":"Mengdi Wang, Woon Sang Cho","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-07T01:41:51Z","title":"Deep Primal-Dual Reinforcement Learning: Accelerating Actor-Critic using Bellman Duality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.02467","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:fa4ab799b2d82135f5bc41c8cf8fc6f3a7d56a84f040f93dae7b81f8a777d44b","target":"record","created_at":"2026-05-18T00:28:34Z","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":"477d6389148794066ffc93972132bbfd5ca5a55e8f5f3f07604a54087c6f7f7c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-07T01:41:51Z","title_canon_sha256":"939a9bcefef8e959a06b9ef41ed3ff4e699d23f697074da7737830575854d13d"},"schema_version":"1.0","source":{"id":"1712.02467","kind":"arxiv","version":1}},"canonical_sha256":"9bed224fa37d49931ecef30f1b64db93bc36c310cdbfdb245cf0e2caf292c3ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bed224fa37d49931ecef30f1b64db93bc36c310cdbfdb245cf0e2caf292c3ef","first_computed_at":"2026-05-18T00:28:34.045808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:34.045808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lfuK9dJnYQbxH6EbU8RSZ+ES72je7/qICQE3SBfkSA0MzZXa8yCli6KDHqIo+IYuM6Et30Seqm4yxW01MFUfBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:34.046577Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.02467","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa4ab799b2d82135f5bc41c8cf8fc6f3a7d56a84f040f93dae7b81f8a777d44b","sha256:028c628d60a706c6805181ff7269b45f42a08c26fb9ba088b54b282315f6c047"],"state_sha256":"d8662a5bf9e42c3179c83a98687dfd940a71555a726a9e99c72c7752a342ef85"}