{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:G3IWULP4GMSRMOJVO6BTJS5NAW","short_pith_number":"pith:G3IWULP4","schema_version":"1.0","canonical_sha256":"36d16a2dfc3325163935778334cbad05a300898deac6ac55ca30b269ac3338da","source":{"kind":"arxiv","id":"1712.10282","version":1},"attestation_state":"computed","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"},"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":"1712.10282","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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1712.10282","created_at":"2026-05-18T00:27:03.523149+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.10282v1","created_at":"2026-05-18T00:27:03.523149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.10282","created_at":"2026-05-18T00:27:03.523149+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3IWULP4GMSR","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3IWULP4GMSRMOJV","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3IWULP4","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2005.01643","citing_title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","ref_index":286,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3IWULP4GMSRMOJVO6BTJS5NAW","json":"https://pith.science/pith/G3IWULP4GMSRMOJVO6BTJS5NAW.json","graph_json":"https://pith.science/api/pith-number/G3IWULP4GMSRMOJVO6BTJS5NAW/graph.json","events_json":"https://pith.science/api/pith-number/G3IWULP4GMSRMOJVO6BTJS5NAW/events.json","paper":"https://pith.science/paper/G3IWULP4"},"agent_actions":{"view_html":"https://pith.science/pith/G3IWULP4GMSRMOJVO6BTJS5NAW","download_json":"https://pith.science/pith/G3IWULP4GMSRMOJVO6BTJS5NAW.json","view_paper":"https://pith.science/paper/G3IWULP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.10282&json=true","fetch_graph":"https://pith.science/api/pith-number/G3IWULP4GMSRMOJVO6BTJS5NAW/graph.json","fetch_events":"https://pith.science/api/pith-number/G3IWULP4GMSRMOJVO6BTJS5NAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3IWULP4GMSRMOJVO6BTJS5NAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3IWULP4GMSRMOJVO6BTJS5NAW/action/storage_attestation","attest_author":"https://pith.science/pith/G3IWULP4GMSRMOJVO6BTJS5NAW/action/author_attestation","sign_citation":"https://pith.science/pith/G3IWULP4GMSRMOJVO6BTJS5NAW/action/citation_signature","submit_replication":"https://pith.science/pith/G3IWULP4GMSRMOJVO6BTJS5NAW/action/replication_record"}},"created_at":"2026-05-18T00:27:03.523149+00:00","updated_at":"2026-05-18T00:27:03.523149+00:00"}