{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IVAOG2KGPXMGUIQRLVY2MDGRYR","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":"6ade567d343adb1ac997243d21ad3fc678e8bcfae2086f028e7a6cbf69b9c2f1","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-08T18:05:18Z","title_canon_sha256":"53dca9e42f72c1699394ca0800612aab82b8f4aa8c9cb8fa73d57adf6d984f99"},"schema_version":"1.0","source":{"id":"1803.03232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.03232","created_at":"2026-05-18T00:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"1803.03232v1","created_at":"2026-05-18T00:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.03232","created_at":"2026-05-18T00:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"IVAOG2KGPXMG","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IVAOG2KGPXMGUIQR","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IVAOG2KG","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:f802bf0dc60d4ed5bac2dea080b5af974888cfe9355770ef2fd943ad0bbeafb7","target":"graph","created_at":"2026-05-18T00:21:44Z","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":"Reinforcement learning (RL) is a promising approach to solve dialogue policy optimisation. Traditional RL algorithms, however, fail to scale to large domains due to the curse of dimensionality. We propose a novel Dialogue Management architecture, based on Feudal RL, which decomposes the decision into two steps; a first step where a master policy selects a subset of primitive actions, and a second step where a primitive action is chosen from the selected subset. The structural information included in the domain ontology is used to abstract the dialogue state space, taking the decisions at each ","authors_text":"Bo-Hsiang Tseng, I\\~nigo Casanueva, Lina Rojas-Barahona, Milica Ga\\v{s}i\\'c, Pawe{\\l} Budzianowski, Pei-Hao Su, Stefan Ultes","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-08T18:05:18Z","title":"Feudal Reinforcement Learning for Dialogue Management in Large Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.03232","kind":"arxiv","version":1},"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":"sha256:1c1f27e969e384abb0689c704d73e9035bac9a0048068469f5e68c6d5c27a9f5","target":"record","created_at":"2026-05-18T00:21:44Z","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":"6ade567d343adb1ac997243d21ad3fc678e8bcfae2086f028e7a6cbf69b9c2f1","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-08T18:05:18Z","title_canon_sha256":"53dca9e42f72c1699394ca0800612aab82b8f4aa8c9cb8fa73d57adf6d984f99"},"schema_version":"1.0","source":{"id":"1803.03232","kind":"arxiv","version":1}},"canonical_sha256":"4540e369467dd86a22115d71a60cd1c447b1a7d0cf4fd1df08ced7c449b28d79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4540e369467dd86a22115d71a60cd1c447b1a7d0cf4fd1df08ced7c449b28d79","first_computed_at":"2026-05-18T00:21:44.046342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:21:44.046342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i6fqYWq5J5NNs5o4Mp0CPdwDJ5NiDnxVK2ao38ogzCY29jylCoSWHtjlQg4BqiOdoOK3fR5+t7R4kcR3onmZCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:21:44.047204Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.03232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c1f27e969e384abb0689c704d73e9035bac9a0048068469f5e68c6d5c27a9f5","sha256:f802bf0dc60d4ed5bac2dea080b5af974888cfe9355770ef2fd943ad0bbeafb7"],"state_sha256":"8d0bd1b4f71917cae8de959c9c9ee0228061aaaff31d6210600bfd4f09f87404"}