{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:57XR3W3TN74OOMQUZULBWMQYFF","short_pith_number":"pith:57XR3W3T","schema_version":"1.0","canonical_sha256":"efef1ddb736ff8e73214cd161b321829456b7b668320ae2cee798fc7299a6139","source":{"kind":"arxiv","id":"2004.03809","version":2},"attestation_state":"computed","paper":{"title":"Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Minlie Huang, Runze Liang, Ryuichi Takanobu","submitted_at":"2020-04-08T04:51:40Z","abstract_excerpt":"Many studies have applied reinforcement learning to train a dialog policy and show great promise these years. One common approach is to employ a user simulator to obtain a large number of simulated user experiences for reinforcement learning algorithms. However, modeling a realistic user simulator is challenging. A rule-based simulator requires heavy domain expertise for complex tasks, and a data-driven simulator requires considerable data and it is even unclear how to evaluate a simulator. To avoid explicitly building a user simulator beforehand, we propose Multi-Agent Dialog Policy Learning,"},"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":"2004.03809","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-08T04:51:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a725279ac1a65111ddf52c65c7ee198846a0be4fa53e2c55af5156076707513","abstract_canon_sha256":"2b8a6fd2b8973f09404ab9ffaf22d2fa52671b470436e2f5940d2cd147f3873a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:35.595616Z","signature_b64":"2v3ahne0nEjBNhBxNqKD6JqHI93yWJjU5P4L/DD8nc4XajtH1UXRmCAg5nXOdXLaNt9qYYHVduik/qBqu98gCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efef1ddb736ff8e73214cd161b321829456b7b668320ae2cee798fc7299a6139","last_reissued_at":"2026-07-05T00:57:35.595231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:35.595231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Minlie Huang, Runze Liang, Ryuichi Takanobu","submitted_at":"2020-04-08T04:51:40Z","abstract_excerpt":"Many studies have applied reinforcement learning to train a dialog policy and show great promise these years. One common approach is to employ a user simulator to obtain a large number of simulated user experiences for reinforcement learning algorithms. However, modeling a realistic user simulator is challenging. A rule-based simulator requires heavy domain expertise for complex tasks, and a data-driven simulator requires considerable data and it is even unclear how to evaluate a simulator. To avoid explicitly building a user simulator beforehand, we propose Multi-Agent Dialog Policy Learning,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03809","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.03809/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2004.03809","created_at":"2026-07-05T00:57:35.595280+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.03809v2","created_at":"2026-07-05T00:57:35.595280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03809","created_at":"2026-07-05T00:57:35.595280+00:00"},{"alias_kind":"pith_short_12","alias_value":"57XR3W3TN74O","created_at":"2026-07-05T00:57:35.595280+00:00"},{"alias_kind":"pith_short_16","alias_value":"57XR3W3TN74OOMQU","created_at":"2026-07-05T00:57:35.595280+00:00"},{"alias_kind":"pith_short_8","alias_value":"57XR3W3T","created_at":"2026-07-05T00:57:35.595280+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19652","citing_title":"Tailored Conversations beyond LLMs: A RL-Based Dialogue Manager","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57XR3W3TN74OOMQUZULBWMQYFF","json":"https://pith.science/pith/57XR3W3TN74OOMQUZULBWMQYFF.json","graph_json":"https://pith.science/api/pith-number/57XR3W3TN74OOMQUZULBWMQYFF/graph.json","events_json":"https://pith.science/api/pith-number/57XR3W3TN74OOMQUZULBWMQYFF/events.json","paper":"https://pith.science/paper/57XR3W3T"},"agent_actions":{"view_html":"https://pith.science/pith/57XR3W3TN74OOMQUZULBWMQYFF","download_json":"https://pith.science/pith/57XR3W3TN74OOMQUZULBWMQYFF.json","view_paper":"https://pith.science/paper/57XR3W3T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.03809&json=true","fetch_graph":"https://pith.science/api/pith-number/57XR3W3TN74OOMQUZULBWMQYFF/graph.json","fetch_events":"https://pith.science/api/pith-number/57XR3W3TN74OOMQUZULBWMQYFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57XR3W3TN74OOMQUZULBWMQYFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57XR3W3TN74OOMQUZULBWMQYFF/action/storage_attestation","attest_author":"https://pith.science/pith/57XR3W3TN74OOMQUZULBWMQYFF/action/author_attestation","sign_citation":"https://pith.science/pith/57XR3W3TN74OOMQUZULBWMQYFF/action/citation_signature","submit_replication":"https://pith.science/pith/57XR3W3TN74OOMQUZULBWMQYFF/action/replication_record"}},"created_at":"2026-07-05T00:57:35.595280+00:00","updated_at":"2026-07-05T00:57:35.595280+00:00"}