{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XROFMLXNPRGQRJSIIWJJFJMZP4","short_pith_number":"pith:XROFMLXN","schema_version":"1.0","canonical_sha256":"bc5c562eed7c4d08a648459292a5997f3bc3a06700c282cd559ef88bfa0ab4d6","source":{"kind":"arxiv","id":"1808.06497","version":2},"attestation_state":"computed","paper":{"title":"Goal-oriented Dialogue Policy Learning from Failures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Keting Lu, Shiqi Zhang, Xiaoping Chen","submitted_at":"2018-08-20T15:04:30Z","abstract_excerpt":"Reinforcement learning methods have been used for learning dialogue policies. However, learning an effective dialogue policy frequently requires prohibitively many conversations. This is partly because of the sparse rewards in dialogues, and the very few successful dialogues in early learning phase. Hindsight experience replay (HER) enables learning from failures, but the vanilla HER is inapplicable to dialogue learning due to the implicit goals. In this work, we develop two complex HER methods providing different trade-offs between complexity and performance, and, for the first time, enabled "},"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":"1808.06497","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-08-20T15:04:30Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"433ab2089daedda8db4cb0ff9e465e907dbcf31d548c1a31850006dc75eae823","abstract_canon_sha256":"16c371f046c91a890e593138a8b5ffbcdfa957a3838d3e11d1a6550eb5b1ff9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:08.166659Z","signature_b64":"/00tUgx3QHeIDgQOrurkSeIYwwWjgWOm/Lr8EyIoLtK5BnmuIdzzRCVaRfKkhJb/vjRmne47PU2O8tOMoYK3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc5c562eed7c4d08a648459292a5997f3bc3a06700c282cd559ef88bfa0ab4d6","last_reissued_at":"2026-05-18T00:00:08.166144Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:08.166144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Goal-oriented Dialogue Policy Learning from Failures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Keting Lu, Shiqi Zhang, Xiaoping Chen","submitted_at":"2018-08-20T15:04:30Z","abstract_excerpt":"Reinforcement learning methods have been used for learning dialogue policies. However, learning an effective dialogue policy frequently requires prohibitively many conversations. This is partly because of the sparse rewards in dialogues, and the very few successful dialogues in early learning phase. Hindsight experience replay (HER) enables learning from failures, but the vanilla HER is inapplicable to dialogue learning due to the implicit goals. In this work, we develop two complex HER methods providing different trade-offs between complexity and performance, and, for the first time, enabled "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.06497","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":""},"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":"1808.06497","created_at":"2026-05-18T00:00:08.166226+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.06497v2","created_at":"2026-05-18T00:00:08.166226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.06497","created_at":"2026-05-18T00:00:08.166226+00:00"},{"alias_kind":"pith_short_12","alias_value":"XROFMLXNPRGQ","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XROFMLXNPRGQRJSI","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XROFMLXN","created_at":"2026-05-18T12:33:01.666342+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/XROFMLXNPRGQRJSIIWJJFJMZP4","json":"https://pith.science/pith/XROFMLXNPRGQRJSIIWJJFJMZP4.json","graph_json":"https://pith.science/api/pith-number/XROFMLXNPRGQRJSIIWJJFJMZP4/graph.json","events_json":"https://pith.science/api/pith-number/XROFMLXNPRGQRJSIIWJJFJMZP4/events.json","paper":"https://pith.science/paper/XROFMLXN"},"agent_actions":{"view_html":"https://pith.science/pith/XROFMLXNPRGQRJSIIWJJFJMZP4","download_json":"https://pith.science/pith/XROFMLXNPRGQRJSIIWJJFJMZP4.json","view_paper":"https://pith.science/paper/XROFMLXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.06497&json=true","fetch_graph":"https://pith.science/api/pith-number/XROFMLXNPRGQRJSIIWJJFJMZP4/graph.json","fetch_events":"https://pith.science/api/pith-number/XROFMLXNPRGQRJSIIWJJFJMZP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XROFMLXNPRGQRJSIIWJJFJMZP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XROFMLXNPRGQRJSIIWJJFJMZP4/action/storage_attestation","attest_author":"https://pith.science/pith/XROFMLXNPRGQRJSIIWJJFJMZP4/action/author_attestation","sign_citation":"https://pith.science/pith/XROFMLXNPRGQRJSIIWJJFJMZP4/action/citation_signature","submit_replication":"https://pith.science/pith/XROFMLXNPRGQRJSIIWJJFJMZP4/action/replication_record"}},"created_at":"2026-05-18T00:00:08.166226+00:00","updated_at":"2026-05-18T00:00:08.166226+00:00"}