{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XCJ32V7KOC4SXWU6YXPDVKJAMI","short_pith_number":"pith:XCJ32V7K","schema_version":"1.0","canonical_sha256":"b893bd57ea70b92bda9ec5de3aa92062364ce6d9324c6cab138c680f26ebf860","source":{"kind":"arxiv","id":"1903.01344","version":3},"attestation_state":"computed","paper":{"title":"Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rui Su, Weinan Zhang, Yong Yu, Zhou Fan","submitted_at":"2019-03-04T16:33:15Z","abstract_excerpt":"In this paper we propose a hybrid architecture of actor-critic algorithms for reinforcement learning in parameterized action space, which consists of multiple parallel sub-actor networks to decompose the structured action space into simpler action spaces along with a critic network to guide the training of all sub-actor networks. While this paper is mainly focused on parameterized action space, the proposed architecture, which we call hybrid actor-critic, can be extended for more general action spaces which has a hierarchical structure. We present an instance of the hybrid actor-critic archite"},"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":"1903.01344","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-04T16:33:15Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5c190bacf98fb040c482bd8a726fdc6a093df7d7e03658eea275e6bf16706a7f","abstract_canon_sha256":"f7e21934aefa9ed7502eff85ec5da363d06fbe46e29ddb9a4c1b107d6155f771"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:42.426824Z","signature_b64":"2U4OlaWuB8symG656CUZWfDbY3Bv+7uoU4rlFDyOPuQmPpYx/gV2SpRwmWOCJ1lI6Yg9esD3RcYNwf/w7gmmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b893bd57ea70b92bda9ec5de3aa92062364ce6d9324c6cab138c680f26ebf860","last_reissued_at":"2026-05-17T23:44:42.426178Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:42.426178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rui Su, Weinan Zhang, Yong Yu, Zhou Fan","submitted_at":"2019-03-04T16:33:15Z","abstract_excerpt":"In this paper we propose a hybrid architecture of actor-critic algorithms for reinforcement learning in parameterized action space, which consists of multiple parallel sub-actor networks to decompose the structured action space into simpler action spaces along with a critic network to guide the training of all sub-actor networks. While this paper is mainly focused on parameterized action space, the proposed architecture, which we call hybrid actor-critic, can be extended for more general action spaces which has a hierarchical structure. We present an instance of the hybrid actor-critic archite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.01344","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":"1903.01344","created_at":"2026-05-17T23:44:42.426285+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.01344v3","created_at":"2026-05-17T23:44:42.426285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.01344","created_at":"2026-05-17T23:44:42.426285+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCJ32V7KOC4S","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCJ32V7KOC4SXWU6","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCJ32V7K","created_at":"2026-05-18T12:33:33.725879+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/XCJ32V7KOC4SXWU6YXPDVKJAMI","json":"https://pith.science/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI.json","graph_json":"https://pith.science/api/pith-number/XCJ32V7KOC4SXWU6YXPDVKJAMI/graph.json","events_json":"https://pith.science/api/pith-number/XCJ32V7KOC4SXWU6YXPDVKJAMI/events.json","paper":"https://pith.science/paper/XCJ32V7K"},"agent_actions":{"view_html":"https://pith.science/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI","download_json":"https://pith.science/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI.json","view_paper":"https://pith.science/paper/XCJ32V7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.01344&json=true","fetch_graph":"https://pith.science/api/pith-number/XCJ32V7KOC4SXWU6YXPDVKJAMI/graph.json","fetch_events":"https://pith.science/api/pith-number/XCJ32V7KOC4SXWU6YXPDVKJAMI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI/action/storage_attestation","attest_author":"https://pith.science/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI/action/author_attestation","sign_citation":"https://pith.science/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI/action/citation_signature","submit_replication":"https://pith.science/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI/action/replication_record"}},"created_at":"2026-05-17T23:44:42.426285+00:00","updated_at":"2026-05-17T23:44:42.426285+00:00"}