{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LJ65SKPZP57WVHUB6EEMV3JVYA","short_pith_number":"pith:LJ65SKPZ","schema_version":"1.0","canonical_sha256":"5a7dd929f97f7f6a9e81f108caed35c020fbd9a54a33f665e60ff4e71fa8198f","source":{"kind":"arxiv","id":"1703.01161","version":2},"attestation_state":"computed","paper":{"title":"FeUdal Networks for Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Sasha Vezhnevets, David Silver, Koray Kavukcuoglu, Max Jaderberg, Nicolas Heess, Simon Osindero, Tom Schaul","submitted_at":"2017-03-03T14:05:11Z","abstract_excerpt":"We introduce FeUdal Networks (FuNs): a novel architecture for hierarchical reinforcement learning. Our approach is inspired by the feudal reinforcement learning proposal of Dayan and Hinton, and gains power and efficacy by decoupling end-to-end learning across multiple levels -- allowing it to utilise different resolutions of time. Our framework employs a Manager module and a Worker module. The Manager operates at a lower temporal resolution and sets abstract goals which are conveyed to and enacted by the Worker. The Worker generates primitive actions at every tick of the environment. The deco"},"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":"1703.01161","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T14:05:11Z","cross_cats_sorted":[],"title_canon_sha256":"7b40339175935817d90e79c1db2ea0fadf01894212efa825ce959a497c6d58c0","abstract_canon_sha256":"7942c3de31180f593adc2032c4844288085f49cb3082b76f144063a1c8fd0e7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:31.186089Z","signature_b64":"5lBTD2l4TqnYapo2iJJzL2ODdw+NxzpDngyS/D4uL1uSV2BYwgqghyRgeQH1B0CIN8JAhkUHjk6EpZ9/+8FIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a7dd929f97f7f6a9e81f108caed35c020fbd9a54a33f665e60ff4e71fa8198f","last_reissued_at":"2026-05-18T00:49:31.185475Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:31.185475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FeUdal Networks for Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Sasha Vezhnevets, David Silver, Koray Kavukcuoglu, Max Jaderberg, Nicolas Heess, Simon Osindero, Tom Schaul","submitted_at":"2017-03-03T14:05:11Z","abstract_excerpt":"We introduce FeUdal Networks (FuNs): a novel architecture for hierarchical reinforcement learning. Our approach is inspired by the feudal reinforcement learning proposal of Dayan and Hinton, and gains power and efficacy by decoupling end-to-end learning across multiple levels -- allowing it to utilise different resolutions of time. Our framework employs a Manager module and a Worker module. The Manager operates at a lower temporal resolution and sets abstract goals which are conveyed to and enacted by the Worker. The Worker generates primitive actions at every tick of the environment. The deco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01161","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":"1703.01161","created_at":"2026-05-18T00:49:31.185580+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.01161v2","created_at":"2026-05-18T00:49:31.185580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01161","created_at":"2026-05-18T00:49:31.185580+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJ65SKPZP57W","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJ65SKPZP57WVHUB","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJ65SKPZ","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.10667","citing_title":"Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LJ65SKPZP57WVHUB6EEMV3JVYA","json":"https://pith.science/pith/LJ65SKPZP57WVHUB6EEMV3JVYA.json","graph_json":"https://pith.science/api/pith-number/LJ65SKPZP57WVHUB6EEMV3JVYA/graph.json","events_json":"https://pith.science/api/pith-number/LJ65SKPZP57WVHUB6EEMV3JVYA/events.json","paper":"https://pith.science/paper/LJ65SKPZ"},"agent_actions":{"view_html":"https://pith.science/pith/LJ65SKPZP57WVHUB6EEMV3JVYA","download_json":"https://pith.science/pith/LJ65SKPZP57WVHUB6EEMV3JVYA.json","view_paper":"https://pith.science/paper/LJ65SKPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.01161&json=true","fetch_graph":"https://pith.science/api/pith-number/LJ65SKPZP57WVHUB6EEMV3JVYA/graph.json","fetch_events":"https://pith.science/api/pith-number/LJ65SKPZP57WVHUB6EEMV3JVYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJ65SKPZP57WVHUB6EEMV3JVYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJ65SKPZP57WVHUB6EEMV3JVYA/action/storage_attestation","attest_author":"https://pith.science/pith/LJ65SKPZP57WVHUB6EEMV3JVYA/action/author_attestation","sign_citation":"https://pith.science/pith/LJ65SKPZP57WVHUB6EEMV3JVYA/action/citation_signature","submit_replication":"https://pith.science/pith/LJ65SKPZP57WVHUB6EEMV3JVYA/action/replication_record"}},"created_at":"2026-05-18T00:49:31.185580+00:00","updated_at":"2026-05-18T00:49:31.185580+00:00"}