{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:G3IWULP4GMSRMOJVO6BTJS5NAW","short_pith_number":"pith:G3IWULP4","canonical_record":{"source":{"id":"1712.10282","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-29T17:17:58Z","cross_cats_sorted":[],"title_canon_sha256":"3569ec00e66ff22a93b79d21c9f92446571a1c030d1459c6bf09b2a6d511b872","abstract_canon_sha256":"c8bc8285af1a3ce02c015515fd129827ace30c3d75d320f1dc7a19c7c7f4ff74"},"schema_version":"1.0"},"canonical_sha256":"36d16a2dfc3325163935778334cbad05a300898deac6ac55ca30b269ac3338da","source":{"kind":"arxiv","id":"1712.10282","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.10282","created_at":"2026-05-18T00:27:03Z"},{"alias_kind":"arxiv_version","alias_value":"1712.10282v1","created_at":"2026-05-18T00:27:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.10282","created_at":"2026-05-18T00:27:03Z"},{"alias_kind":"pith_short_12","alias_value":"G3IWULP4GMSR","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"G3IWULP4GMSRMOJV","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"G3IWULP4","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:G3IWULP4GMSRMOJVO6BTJS5NAW","target":"record","payload":{"canonical_record":{"source":{"id":"1712.10282","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-29T17:17:58Z","cross_cats_sorted":[],"title_canon_sha256":"3569ec00e66ff22a93b79d21c9f92446571a1c030d1459c6bf09b2a6d511b872","abstract_canon_sha256":"c8bc8285af1a3ce02c015515fd129827ace30c3d75d320f1dc7a19c7c7f4ff74"},"schema_version":"1.0"},"canonical_sha256":"36d16a2dfc3325163935778334cbad05a300898deac6ac55ca30b269ac3338da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:03.523581Z","signature_b64":"/5XwTE9ywYLcpCufO0x970K80pjH4e24mxR1PNi4AZGqMPX+7lEE4Hn7CaKBqMxJ40/WpUO8a8CMK2KZbBfRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36d16a2dfc3325163935778334cbad05a300898deac6ac55ca30b269ac3338da","last_reissued_at":"2026-05-18T00:27:03.523069Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:03.523069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.10282","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:27:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"olA58ZrC4HRulSESmAR1hgrtow8qGQQzz3cA0oXj04pbj1AjWMSZC69ieKFcg1P0d2nQ9lHqcbcJBgVHH4CFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T07:55:53.976000Z"},"content_sha256":"f985bb40a7b2f5d75850e6c4a5a0ee3b6b8ad0a1fc862111f22363afa5cffee7","schema_version":"1.0","event_id":"sha256:f985bb40a7b2f5d75850e6c4a5a0ee3b6b8ad0a1fc862111f22363afa5cffee7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:G3IWULP4GMSRMOJVO6BTJS5NAW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting the Actor with Dual Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Albert Shaw, Bo Dai, Le Song, Lihong Li, Niao He","submitted_at":"2017-12-29T17:17:58Z","abstract_excerpt":"This paper proposes a new actor-critic-style algorithm called Dual Actor-Critic or Dual-AC. It is derived in a principled way from the Lagrangian dual form of the Bellman optimality equation, which can be viewed as a two-player game between the actor and a critic-like function, which is named as dual critic. Compared to its actor-critic relatives, Dual-AC has the desired property that the actor and dual critic are updated cooperatively to optimize the same objective function, providing a more transparent way for learning the critic that is directly related to the objective function of the acto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.10282","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:27:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eXrUw/u3QSO6zsUERZbKObZbGDr3pEpvr0bSyEij/rQsbrLJDENgTvhfsttAysARlFO1rYwYALa7qVBWPoHkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T07:55:53.976616Z"},"content_sha256":"3e027d2a767fedd571a095c4b0d4fe9400a289230a4b7119016286d921388604","schema_version":"1.0","event_id":"sha256:3e027d2a767fedd571a095c4b0d4fe9400a289230a4b7119016286d921388604"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G3IWULP4GMSRMOJVO6BTJS5NAW/bundle.json","state_url":"https://pith.science/pith/G3IWULP4GMSRMOJVO6BTJS5NAW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G3IWULP4GMSRMOJVO6BTJS5NAW/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":"2026-05-23T07:55:53Z","links":{"resolver":"https://pith.science/pith/G3IWULP4GMSRMOJVO6BTJS5NAW","bundle":"https://pith.science/pith/G3IWULP4GMSRMOJVO6BTJS5NAW/bundle.json","state":"https://pith.science/pith/G3IWULP4GMSRMOJVO6BTJS5NAW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G3IWULP4GMSRMOJVO6BTJS5NAW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:G3IWULP4GMSRMOJVO6BTJS5NAW","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":"c8bc8285af1a3ce02c015515fd129827ace30c3d75d320f1dc7a19c7c7f4ff74","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-29T17:17:58Z","title_canon_sha256":"3569ec00e66ff22a93b79d21c9f92446571a1c030d1459c6bf09b2a6d511b872"},"schema_version":"1.0","source":{"id":"1712.10282","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.10282","created_at":"2026-05-18T00:27:03Z"},{"alias_kind":"arxiv_version","alias_value":"1712.10282v1","created_at":"2026-05-18T00:27:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.10282","created_at":"2026-05-18T00:27:03Z"},{"alias_kind":"pith_short_12","alias_value":"G3IWULP4GMSR","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"G3IWULP4GMSRMOJV","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"G3IWULP4","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:3e027d2a767fedd571a095c4b0d4fe9400a289230a4b7119016286d921388604","target":"graph","created_at":"2026-05-18T00:27:03Z","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"},"paper":{"abstract_excerpt":"This paper proposes a new actor-critic-style algorithm called Dual Actor-Critic or Dual-AC. It is derived in a principled way from the Lagrangian dual form of the Bellman optimality equation, which can be viewed as a two-player game between the actor and a critic-like function, which is named as dual critic. Compared to its actor-critic relatives, Dual-AC has the desired property that the actor and dual critic are updated cooperatively to optimize the same objective function, providing a more transparent way for learning the critic that is directly related to the objective function of the acto","authors_text":"Albert Shaw, Bo Dai, Le Song, Lihong Li, Niao He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-29T17:17:58Z","title":"Boosting the Actor with Dual Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.10282","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:f985bb40a7b2f5d75850e6c4a5a0ee3b6b8ad0a1fc862111f22363afa5cffee7","target":"record","created_at":"2026-05-18T00:27:03Z","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":"c8bc8285af1a3ce02c015515fd129827ace30c3d75d320f1dc7a19c7c7f4ff74","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-29T17:17:58Z","title_canon_sha256":"3569ec00e66ff22a93b79d21c9f92446571a1c030d1459c6bf09b2a6d511b872"},"schema_version":"1.0","source":{"id":"1712.10282","kind":"arxiv","version":1}},"canonical_sha256":"36d16a2dfc3325163935778334cbad05a300898deac6ac55ca30b269ac3338da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36d16a2dfc3325163935778334cbad05a300898deac6ac55ca30b269ac3338da","first_computed_at":"2026-05-18T00:27:03.523069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:03.523069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/5XwTE9ywYLcpCufO0x970K80pjH4e24mxR1PNi4AZGqMPX+7lEE4Hn7CaKBqMxJ40/WpUO8a8CMK2KZbBfRAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:03.523581Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.10282","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f985bb40a7b2f5d75850e6c4a5a0ee3b6b8ad0a1fc862111f22363afa5cffee7","sha256:3e027d2a767fedd571a095c4b0d4fe9400a289230a4b7119016286d921388604"],"state_sha256":"c4d64ceb7ad8d4a84fe41bbb5bdf986913c512731e30cf8a54500cd689865594"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j0y2IsY0Cj3ZTXqrayRUFigJUa/IHeIjEo1G2ljYpN7kZLLwmAZ2mcELD0/acH0Ej7cbw7mqkCC5/mWuNI5NAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T07:55:53.980115Z","bundle_sha256":"f03a7cc1a9d04982200392f9d8dab8f664da1571be19931fadb32381abffc4c7"}}