{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MV5WWM6TMFVG3WX5P4A7WTCL3C","short_pith_number":"pith:MV5WWM6T","schema_version":"1.0","canonical_sha256":"657b6b33d3616a6ddafd7f01fb4c4bd892eb08e62d2c54c20432cb74327a1cb5","source":{"kind":"arxiv","id":"1905.11259","version":1},"attestation_state":"computed","paper":{"title":"AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bowen Tan, Kai Yu, Lu Chen, Milica Gasic, Sishan Long, Zhi Chen","submitted_at":"2019-05-27T14:27:13Z","abstract_excerpt":"Dialogue policy plays an important role in task-oriented spoken dialogue systems. It determines how to respond to users. The recently proposed deep reinforcement learning (DRL) approaches have been used for policy optimization. However, these deep models are still challenging for two reasons: 1) Many DRL-based policies are not sample-efficient. 2) Most models don't have the capability of policy transfer between different domains. In this paper, we propose a universal framework, AgentGraph, to tackle these two problems. The proposed AgentGraph is the combination of GNN-based architecture and DR"},"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":"1905.11259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-27T14:27:13Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"789f9684982e5193145bcbb698ebff8d3b0e4ee4315fc68e503dd7e0ba090aa6","abstract_canon_sha256":"70a18e82c8c4c9d8ec2f7389a42fea085855a25808362f48a35b6b3c043bf6ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:02.544636Z","signature_b64":"Ze/E7j4w1x5BwRyAyfCNycGn4OsDRc4UIsqAYgCq6L8Eluv6UFWmy7G/fEHyJr3HdgXdFaC6GhS+NVuty9IEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"657b6b33d3616a6ddafd7f01fb4c4bd892eb08e62d2c54c20432cb74327a1cb5","last_reissued_at":"2026-05-17T23:45:02.544241Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:02.544241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bowen Tan, Kai Yu, Lu Chen, Milica Gasic, Sishan Long, Zhi Chen","submitted_at":"2019-05-27T14:27:13Z","abstract_excerpt":"Dialogue policy plays an important role in task-oriented spoken dialogue systems. It determines how to respond to users. The recently proposed deep reinforcement learning (DRL) approaches have been used for policy optimization. However, these deep models are still challenging for two reasons: 1) Many DRL-based policies are not sample-efficient. 2) Most models don't have the capability of policy transfer between different domains. In this paper, we propose a universal framework, AgentGraph, to tackle these two problems. The proposed AgentGraph is the combination of GNN-based architecture and DR"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11259","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":"1905.11259","created_at":"2026-05-17T23:45:02.544303+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11259v1","created_at":"2026-05-17T23:45:02.544303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11259","created_at":"2026-05-17T23:45:02.544303+00:00"},{"alias_kind":"pith_short_12","alias_value":"MV5WWM6TMFVG","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"MV5WWM6TMFVG3WX5","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"MV5WWM6T","created_at":"2026-05-18T12:33:24.271573+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/MV5WWM6TMFVG3WX5P4A7WTCL3C","json":"https://pith.science/pith/MV5WWM6TMFVG3WX5P4A7WTCL3C.json","graph_json":"https://pith.science/api/pith-number/MV5WWM6TMFVG3WX5P4A7WTCL3C/graph.json","events_json":"https://pith.science/api/pith-number/MV5WWM6TMFVG3WX5P4A7WTCL3C/events.json","paper":"https://pith.science/paper/MV5WWM6T"},"agent_actions":{"view_html":"https://pith.science/pith/MV5WWM6TMFVG3WX5P4A7WTCL3C","download_json":"https://pith.science/pith/MV5WWM6TMFVG3WX5P4A7WTCL3C.json","view_paper":"https://pith.science/paper/MV5WWM6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11259&json=true","fetch_graph":"https://pith.science/api/pith-number/MV5WWM6TMFVG3WX5P4A7WTCL3C/graph.json","fetch_events":"https://pith.science/api/pith-number/MV5WWM6TMFVG3WX5P4A7WTCL3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MV5WWM6TMFVG3WX5P4A7WTCL3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MV5WWM6TMFVG3WX5P4A7WTCL3C/action/storage_attestation","attest_author":"https://pith.science/pith/MV5WWM6TMFVG3WX5P4A7WTCL3C/action/author_attestation","sign_citation":"https://pith.science/pith/MV5WWM6TMFVG3WX5P4A7WTCL3C/action/citation_signature","submit_replication":"https://pith.science/pith/MV5WWM6TMFVG3WX5P4A7WTCL3C/action/replication_record"}},"created_at":"2026-05-17T23:45:02.544303+00:00","updated_at":"2026-05-17T23:45:02.544303+00:00"}