{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:F6YZ6QTRVICDUPMSLLXZSDP3EF","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":"9aa329c46abb3616a385ea63e2d8a19eac9546bb6368f9265553c2e0956ee745","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-01T09:56:31Z","title_canon_sha256":"8f5e795c2a414d36b488038ae38af404e8782f4b34543f585497537326a61edc"},"schema_version":"1.0","source":{"id":"1707.00130","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.00130","created_at":"2026-05-18T00:40:53Z"},{"alias_kind":"arxiv_version","alias_value":"1707.00130v2","created_at":"2026-05-18T00:40:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00130","created_at":"2026-05-18T00:40:53Z"},{"alias_kind":"pith_short_12","alias_value":"F6YZ6QTRVICD","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"F6YZ6QTRVICDUPMS","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"F6YZ6QTR","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:a5bf5773499b727041d6ab0379e54306260df8ddadc0b1bdabd0bbd4cd4648cb","target":"graph","created_at":"2026-05-18T00:40:53Z","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":"Deep reinforcement learning (RL) methods have significant potential for dialogue policy optimisation. However, they suffer from a poor performance in the early stages of learning. This is especially problematic for on-line learning with real users. Two approaches are introduced to tackle this problem. Firstly, to speed up the learning process, two sample-efficient neural networks algorithms: trust region actor-critic with experience replay (TRACER) and episodic natural actor-critic with experience replay (eNACER) are presented. For TRACER, the trust region helps to control the learning step si","authors_text":"Milica Gasic, Pawel Budzianowski, Pei-Hao Su, Stefan Ultes, Steve Young","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-01T09:56:31Z","title":"Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00130","kind":"arxiv","version":2},"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":"sha256:82bb755d70a88a7f1a8259ee2768f05a2e4adffab8d1bc4ab824fb491bc73547","target":"record","created_at":"2026-05-18T00:40:53Z","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":"9aa329c46abb3616a385ea63e2d8a19eac9546bb6368f9265553c2e0956ee745","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-01T09:56:31Z","title_canon_sha256":"8f5e795c2a414d36b488038ae38af404e8782f4b34543f585497537326a61edc"},"schema_version":"1.0","source":{"id":"1707.00130","kind":"arxiv","version":2}},"canonical_sha256":"2fb19f4271aa043a3d925aef990dfb215adba88865d5b339b5c40a1a879c7beb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fb19f4271aa043a3d925aef990dfb215adba88865d5b339b5c40a1a879c7beb","first_computed_at":"2026-05-18T00:40:53.680383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:53.680383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3SMuC8lhZOT9yCvp/6+lM1zl35s3M0tvuEJJf2acUJSG8Vg71v8NTKB4+t4KBSXYLn7/9vHsmlJfpEnVV2zSAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:53.680886Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.00130","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82bb755d70a88a7f1a8259ee2768f05a2e4adffab8d1bc4ab824fb491bc73547","sha256:a5bf5773499b727041d6ab0379e54306260df8ddadc0b1bdabd0bbd4cd4648cb"],"state_sha256":"b3d1a78a3a2603181832a13b71b16fa1a82b3fa69724ac020981b06f6618a9ba"}