{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ICYFH7AL2AC4DXB24PURJNFIUN","short_pith_number":"pith:ICYFH7AL","schema_version":"1.0","canonical_sha256":"40b053fc0bd005c1dc3ae3e914b4a8a35fdda659280837067dab709c76c3edc2","source":{"kind":"arxiv","id":"2004.11054","version":2},"attestation_state":"computed","paper":{"title":"Learning Dialog Policies from Weak Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Gabriel Gordon-Hall, Philip John Gorinski, Shay B. Cohen","submitted_at":"2020-04-23T10:22:16Z","abstract_excerpt":"Deep reinforcement learning is a promising approach to training a dialog manager, but current methods struggle with the large state and action spaces of multi-domain dialog systems. Building upon Deep Q-learning from Demonstrations (DQfD), an algorithm that scores highly in difficult Atari games, we leverage dialog data to guide the agent to successfully respond to a user's requests. We make progressively fewer assumptions about the data needed, using labeled, reduced-labeled, and even unlabeled data to train expert demonstrators. We introduce Reinforced Fine-tune Learning, an extension to DQf"},"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":"2004.11054","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-23T10:22:16Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"e24b6a6bd566787c762553e54001fb29057d55f38fc8cdadd72883139f1a1d68","abstract_canon_sha256":"e926a9a1c4dfc3e63739136948f9bc6ae45fa1ef444210af2c49871c69a76fb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:51.717373Z","signature_b64":"EuRx+DVHs8HASANLd5fIUI6tYTMZNdEfa3MKUfhWIB33SYj9t2fmBQD3yvwhtHznpH2M8PohGGTRbIBnBIHqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40b053fc0bd005c1dc3ae3e914b4a8a35fdda659280837067dab709c76c3edc2","last_reissued_at":"2026-07-05T01:26:51.716834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:51.716834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Dialog Policies from Weak Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Gabriel Gordon-Hall, Philip John Gorinski, Shay B. Cohen","submitted_at":"2020-04-23T10:22:16Z","abstract_excerpt":"Deep reinforcement learning is a promising approach to training a dialog manager, but current methods struggle with the large state and action spaces of multi-domain dialog systems. Building upon Deep Q-learning from Demonstrations (DQfD), an algorithm that scores highly in difficult Atari games, we leverage dialog data to guide the agent to successfully respond to a user's requests. We make progressively fewer assumptions about the data needed, using labeled, reduced-labeled, and even unlabeled data to train expert demonstrators. We introduce Reinforced Fine-tune Learning, an extension to DQf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.11054","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/2004.11054/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":"2004.11054","created_at":"2026-07-05T01:26:51.716899+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.11054v2","created_at":"2026-07-05T01:26:51.716899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.11054","created_at":"2026-07-05T01:26:51.716899+00:00"},{"alias_kind":"pith_short_12","alias_value":"ICYFH7AL2AC4","created_at":"2026-07-05T01:26:51.716899+00:00"},{"alias_kind":"pith_short_16","alias_value":"ICYFH7AL2AC4DXB2","created_at":"2026-07-05T01:26:51.716899+00:00"},{"alias_kind":"pith_short_8","alias_value":"ICYFH7AL","created_at":"2026-07-05T01:26:51.716899+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/ICYFH7AL2AC4DXB24PURJNFIUN","json":"https://pith.science/pith/ICYFH7AL2AC4DXB24PURJNFIUN.json","graph_json":"https://pith.science/api/pith-number/ICYFH7AL2AC4DXB24PURJNFIUN/graph.json","events_json":"https://pith.science/api/pith-number/ICYFH7AL2AC4DXB24PURJNFIUN/events.json","paper":"https://pith.science/paper/ICYFH7AL"},"agent_actions":{"view_html":"https://pith.science/pith/ICYFH7AL2AC4DXB24PURJNFIUN","download_json":"https://pith.science/pith/ICYFH7AL2AC4DXB24PURJNFIUN.json","view_paper":"https://pith.science/paper/ICYFH7AL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.11054&json=true","fetch_graph":"https://pith.science/api/pith-number/ICYFH7AL2AC4DXB24PURJNFIUN/graph.json","fetch_events":"https://pith.science/api/pith-number/ICYFH7AL2AC4DXB24PURJNFIUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ICYFH7AL2AC4DXB24PURJNFIUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ICYFH7AL2AC4DXB24PURJNFIUN/action/storage_attestation","attest_author":"https://pith.science/pith/ICYFH7AL2AC4DXB24PURJNFIUN/action/author_attestation","sign_citation":"https://pith.science/pith/ICYFH7AL2AC4DXB24PURJNFIUN/action/citation_signature","submit_replication":"https://pith.science/pith/ICYFH7AL2AC4DXB24PURJNFIUN/action/replication_record"}},"created_at":"2026-07-05T01:26:51.716899+00:00","updated_at":"2026-07-05T01:26:51.716899+00:00"}