{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XORNQB7WYJAW5G6T5HH2HB62BN","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":"ebfc7b3bba0c00fd5022b75b43242d9541b5e078dbd8236ed48fd08ca7dae423","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-18T18:57:33Z","title_canon_sha256":"21128b189693ce007796d7e5e6000a99e89e3a7a9dfa42315cb324954a9b8ea9"},"schema_version":"1.0","source":{"id":"1801.06176","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.06176","created_at":"2026-05-18T00:15:06Z"},{"alias_kind":"arxiv_version","alias_value":"1801.06176v3","created_at":"2026-05-18T00:15:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.06176","created_at":"2026-05-18T00:15:06Z"},{"alias_kind":"pith_short_12","alias_value":"XORNQB7WYJAW","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XORNQB7WYJAW5G6T","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XORNQB7W","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:a7d9566cfbba1b19aed4cf635664d315c77cbb442c442bbd0d295ece7afcf8df","target":"graph","created_at":"2026-05-18T00:15:06Z","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":"Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users. One common alternative is to use a user simulator. However, a user simulator usually lacks the language complexity of human interlocutors and the biases in its design may tend to degrade the agent. To address these issues, we present Deep Dyna-Q, which to our knowledge is the first deep RL framework that integrates planning for task-completion dialogue policy learning. We incorporate into the dialogue agent a model of the environment, referred to as the wor","authors_text":"Baolin Peng, Jianfeng Gao, Jingjing Liu, Kam-Fai Wong, Shang-Yu Su, Xiujun Li","cross_cats":["cs.AI","cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-18T18:57:33Z","title":"Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.06176","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":"sha256:8fbd4c3ef8b9a9b49108a0b7961cc6439821061d9f74435f8ec227d4b49c4f12","target":"record","created_at":"2026-05-18T00:15:06Z","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":"ebfc7b3bba0c00fd5022b75b43242d9541b5e078dbd8236ed48fd08ca7dae423","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-18T18:57:33Z","title_canon_sha256":"21128b189693ce007796d7e5e6000a99e89e3a7a9dfa42315cb324954a9b8ea9"},"schema_version":"1.0","source":{"id":"1801.06176","kind":"arxiv","version":3}},"canonical_sha256":"bba2d807f6c2416e9bd3e9cfa387da0b7b34ec2fa5455c280d24af75d1fb321d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bba2d807f6c2416e9bd3e9cfa387da0b7b34ec2fa5455c280d24af75d1fb321d","first_computed_at":"2026-05-18T00:15:06.139055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:06.139055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d+m3Myf+9Xfjw5NyjK7B4f7wAraLtdas/2tHhKN9Se2k6JmDdW7+c39iJ+iRo/xnvjdi5mkWkq0m2GZDMUs1CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:06.139762Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.06176","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fbd4c3ef8b9a9b49108a0b7961cc6439821061d9f74435f8ec227d4b49c4f12","sha256:a7d9566cfbba1b19aed4cf635664d315c77cbb442c442bbd0d295ece7afcf8df"],"state_sha256":"259653c6a43cb1405dda36ff7e5cd7666bfa5322c09ffbdbb0c79cb1bd64d75c"}