{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XCJ32V7KOC4SXWU6YXPDVKJAMI","short_pith_number":"pith:XCJ32V7K","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"},"canonical_sha256":"b893bd57ea70b92bda9ec5de3aa92062364ce6d9324c6cab138c680f26ebf860","source":{"kind":"arxiv","id":"1903.01344","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.01344","created_at":"2026-05-17T23:44:42Z"},{"alias_kind":"arxiv_version","alias_value":"1903.01344v3","created_at":"2026-05-17T23:44:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.01344","created_at":"2026-05-17T23:44:42Z"},{"alias_kind":"pith_short_12","alias_value":"XCJ32V7KOC4S","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XCJ32V7KOC4SXWU6","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XCJ32V7K","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XCJ32V7KOC4SXWU6YXPDVKJAMI","target":"record","payload":{"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"},"canonical_sha256":"b893bd57ea70b92bda9ec5de3aa92062364ce6d9324c6cab138c680f26ebf860","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"},"source_kind":"arxiv","source_id":"1903.01344","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EjDoVmFLIo7jg7m0Lpm9cbLwPGkHVZs6oX5CBB3ZAtCSUj5rH9RuHDjciEQirlBy+cjk+1bDtIg5NT30eEpfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:08:32.187409Z"},"content_sha256":"21550470a82e92c3deb7db47c6585d88b645fa114fca54e93fa591e3af14e006","schema_version":"1.0","event_id":"sha256:21550470a82e92c3deb7db47c6585d88b645fa114fca54e93fa591e3af14e006"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XCJ32V7KOC4SXWU6YXPDVKJAMI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"anZ+yTPwylx6uTTjWpXRFguNGLLEwm3xhoJp+jaPbNNj8laF9StXuxt+tXECmqK0QKEAj7yJuwFZe3+zdt+JDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:08:32.188070Z"},"content_sha256":"477430e49203c5dcfb11f12ba52414ff37b48ce8945c6628b3a6cc5b7dbebe3a","schema_version":"1.0","event_id":"sha256:477430e49203c5dcfb11f12ba52414ff37b48ce8945c6628b3a6cc5b7dbebe3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI/bundle.json","state_url":"https://pith.science/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI/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":"2026-05-28T22:08:32Z","links":{"resolver":"https://pith.science/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI","bundle":"https://pith.science/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI/bundle.json","state":"https://pith.science/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XCJ32V7KOC4SXWU6YXPDVKJAMI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XCJ32V7KOC4SXWU6YXPDVKJAMI","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":"f7e21934aefa9ed7502eff85ec5da363d06fbe46e29ddb9a4c1b107d6155f771","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-04T16:33:15Z","title_canon_sha256":"5c190bacf98fb040c482bd8a726fdc6a093df7d7e03658eea275e6bf16706a7f"},"schema_version":"1.0","source":{"id":"1903.01344","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.01344","created_at":"2026-05-17T23:44:42Z"},{"alias_kind":"arxiv_version","alias_value":"1903.01344v3","created_at":"2026-05-17T23:44:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.01344","created_at":"2026-05-17T23:44:42Z"},{"alias_kind":"pith_short_12","alias_value":"XCJ32V7KOC4S","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XCJ32V7KOC4SXWU6","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XCJ32V7K","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:477430e49203c5dcfb11f12ba52414ff37b48ce8945c6628b3a6cc5b7dbebe3a","target":"graph","created_at":"2026-05-17T23:44:42Z","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":"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","authors_text":"Rui Su, Weinan Zhang, Yong Yu, Zhou Fan","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-04T16:33:15Z","title":"Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.01344","kind":"arxiv","version":3},"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":"sha256:21550470a82e92c3deb7db47c6585d88b645fa114fca54e93fa591e3af14e006","target":"record","created_at":"2026-05-17T23:44:42Z","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":"f7e21934aefa9ed7502eff85ec5da363d06fbe46e29ddb9a4c1b107d6155f771","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-04T16:33:15Z","title_canon_sha256":"5c190bacf98fb040c482bd8a726fdc6a093df7d7e03658eea275e6bf16706a7f"},"schema_version":"1.0","source":{"id":"1903.01344","kind":"arxiv","version":3}},"canonical_sha256":"b893bd57ea70b92bda9ec5de3aa92062364ce6d9324c6cab138c680f26ebf860","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b893bd57ea70b92bda9ec5de3aa92062364ce6d9324c6cab138c680f26ebf860","first_computed_at":"2026-05-17T23:44:42.426178Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:42.426178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2U4OlaWuB8symG656CUZWfDbY3Bv+7uoU4rlFDyOPuQmPpYx/gV2SpRwmWOCJ1lI6Yg9esD3RcYNwf/w7gmmBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:42.426824Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.01344","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21550470a82e92c3deb7db47c6585d88b645fa114fca54e93fa591e3af14e006","sha256:477430e49203c5dcfb11f12ba52414ff37b48ce8945c6628b3a6cc5b7dbebe3a"],"state_sha256":"99496f47c6947dd463e13f0e62c222006a3f80ef8202893cf1a0b9b78c7954c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WV4y6d/M20zoJCgh3Telp66f/5OLHv4zy5VcaTt0CF+6SsXJw6r13xjjKDe31JFf4cjseqfgQYd+bfXBMKsEDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T22:08:32.191932Z","bundle_sha256":"8efdd1903271ef6ba026280fced433b85f4c593557557a024637e0d96b3357f5"}}