{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5QT65DSZW6BJWJAZBGMSSCS3LV","short_pith_number":"pith:5QT65DSZ","schema_version":"1.0","canonical_sha256":"ec27ee8e59b7829b24190999290a5b5d53be6b5b7fd4d254379bb4dbe476356e","source":{"kind":"arxiv","id":"1811.07550","version":1},"attestation_state":"computed","paper":{"title":"Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Jianfeng Gao, Jingjing Liu, Xiujun Li, Yiming Yang, Yuexin Wu","submitted_at":"2018-11-19T08:23:34Z","abstract_excerpt":"Training task-completion dialogue agents with reinforcement learning usually requires a large number of real user experiences. The Dyna-Q algorithm extends Q-learning by integrating a world model, and thus can effectively boost training efficiency using simulated experiences generated by the world model. The effectiveness of Dyna-Q, however, depends on the quality of the world model - or implicitly, the pre-specified ratio of real vs. simulated experiences used for Q-learning. To this end, we extend the recently proposed Deep Dyna-Q (DDQ) framework by integrating a switcher that automatically "},"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":"1811.07550","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-19T08:23:34Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"d3eabf88b347b503a7a54d1dd0e5b7c46b25e17e58a1d40f755ab4a3b03020de","abstract_canon_sha256":"331fcb10d30bbbeb866cf1e007add43a767c14462c31214f63daae3a7ab275ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:24.126212Z","signature_b64":"5DBGZBx2bfzbTdFpYmoKMn7IwBCBDhl016+Qkth1gVOpEHGDC2Yu+4NYxx1Menhsd2mMiNliq69jkFMb/VzvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec27ee8e59b7829b24190999290a5b5d53be6b5b7fd4d254379bb4dbe476356e","last_reissued_at":"2026-05-18T00:00:24.125736Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:24.125736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Jianfeng Gao, Jingjing Liu, Xiujun Li, Yiming Yang, Yuexin Wu","submitted_at":"2018-11-19T08:23:34Z","abstract_excerpt":"Training task-completion dialogue agents with reinforcement learning usually requires a large number of real user experiences. The Dyna-Q algorithm extends Q-learning by integrating a world model, and thus can effectively boost training efficiency using simulated experiences generated by the world model. The effectiveness of Dyna-Q, however, depends on the quality of the world model - or implicitly, the pre-specified ratio of real vs. simulated experiences used for Q-learning. To this end, we extend the recently proposed Deep Dyna-Q (DDQ) framework by integrating a switcher that automatically "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07550","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":"1811.07550","created_at":"2026-05-18T00:00:24.125828+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.07550v1","created_at":"2026-05-18T00:00:24.125828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07550","created_at":"2026-05-18T00:00:24.125828+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QT65DSZW6BJ","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QT65DSZW6BJWJAZ","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QT65DSZ","created_at":"2026-05-18T12:32:08.215937+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/5QT65DSZW6BJWJAZBGMSSCS3LV","json":"https://pith.science/pith/5QT65DSZW6BJWJAZBGMSSCS3LV.json","graph_json":"https://pith.science/api/pith-number/5QT65DSZW6BJWJAZBGMSSCS3LV/graph.json","events_json":"https://pith.science/api/pith-number/5QT65DSZW6BJWJAZBGMSSCS3LV/events.json","paper":"https://pith.science/paper/5QT65DSZ"},"agent_actions":{"view_html":"https://pith.science/pith/5QT65DSZW6BJWJAZBGMSSCS3LV","download_json":"https://pith.science/pith/5QT65DSZW6BJWJAZBGMSSCS3LV.json","view_paper":"https://pith.science/paper/5QT65DSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.07550&json=true","fetch_graph":"https://pith.science/api/pith-number/5QT65DSZW6BJWJAZBGMSSCS3LV/graph.json","fetch_events":"https://pith.science/api/pith-number/5QT65DSZW6BJWJAZBGMSSCS3LV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QT65DSZW6BJWJAZBGMSSCS3LV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QT65DSZW6BJWJAZBGMSSCS3LV/action/storage_attestation","attest_author":"https://pith.science/pith/5QT65DSZW6BJWJAZBGMSSCS3LV/action/author_attestation","sign_citation":"https://pith.science/pith/5QT65DSZW6BJWJAZBGMSSCS3LV/action/citation_signature","submit_replication":"https://pith.science/pith/5QT65DSZW6BJWJAZBGMSSCS3LV/action/replication_record"}},"created_at":"2026-05-18T00:00:24.125828+00:00","updated_at":"2026-05-18T00:00:24.125828+00:00"}