{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:IV6IQ7MMMTAQ37JBEVBDJ54V5X","short_pith_number":"pith:IV6IQ7MM","schema_version":"1.0","canonical_sha256":"457c887d8c64c10dfd21254234f795edc693e856bbe84c8f8dd51fd84c4eaf85","source":{"kind":"arxiv","id":"1611.06824","version":3},"attestation_state":"computed","paper":{"title":"Options Discovery with Budgeted Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aur\\'elia L\\'eon, Ludovic Denoyer","submitted_at":"2016-11-21T15:05:55Z","abstract_excerpt":"We consider the problem of learning hierarchical policies for Reinforcement Learning able to discover options, an option corresponding to a sub-policy over a set of primitive actions. Different models have been proposed during the last decade that usually rely on a predefined set of options. We specifically address the problem of automatically discovering options in decision processes. We describe a new learning model called Budgeted Option Neural Network (BONN) able to discover options based on a budgeted learning objective. The BONN model is evaluated on different classical RL problems, demo"},"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":"1611.06824","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-21T15:05:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73fc6cd5265459040ea7aa290444c6a0dfb845c1736a47f7a6504b38518acede","abstract_canon_sha256":"63354b007ff9011b6096f3e2567c9be3a7786cc1b2a909587313438cc5c6f5b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:12.299044Z","signature_b64":"BO4sTqmg722xh9g5nx7mN2u8rKkaDSRAKdAhbqsrNW1tRFRdjBH16Mibg2NrxrePJ2Z+ekj7HEfEn1Dy8xn5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"457c887d8c64c10dfd21254234f795edc693e856bbe84c8f8dd51fd84c4eaf85","last_reissued_at":"2026-05-18T00:50:12.298645Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:12.298645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Options Discovery with Budgeted Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aur\\'elia L\\'eon, Ludovic Denoyer","submitted_at":"2016-11-21T15:05:55Z","abstract_excerpt":"We consider the problem of learning hierarchical policies for Reinforcement Learning able to discover options, an option corresponding to a sub-policy over a set of primitive actions. Different models have been proposed during the last decade that usually rely on a predefined set of options. We specifically address the problem of automatically discovering options in decision processes. We describe a new learning model called Budgeted Option Neural Network (BONN) able to discover options based on a budgeted learning objective. The BONN model is evaluated on different classical RL problems, demo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06824","kind":"arxiv","version":3},"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":"1611.06824","created_at":"2026-05-18T00:50:12.298702+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.06824v3","created_at":"2026-05-18T00:50:12.298702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06824","created_at":"2026-05-18T00:50:12.298702+00:00"},{"alias_kind":"pith_short_12","alias_value":"IV6IQ7MMMTAQ","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_16","alias_value":"IV6IQ7MMMTAQ37JB","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_8","alias_value":"IV6IQ7MM","created_at":"2026-05-18T12:30:22.444734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.00664","citing_title":"Learning World Graphs to Accelerate Hierarchical Reinforcement Learning","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X","json":"https://pith.science/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X.json","graph_json":"https://pith.science/api/pith-number/IV6IQ7MMMTAQ37JBEVBDJ54V5X/graph.json","events_json":"https://pith.science/api/pith-number/IV6IQ7MMMTAQ37JBEVBDJ54V5X/events.json","paper":"https://pith.science/paper/IV6IQ7MM"},"agent_actions":{"view_html":"https://pith.science/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X","download_json":"https://pith.science/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X.json","view_paper":"https://pith.science/paper/IV6IQ7MM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.06824&json=true","fetch_graph":"https://pith.science/api/pith-number/IV6IQ7MMMTAQ37JBEVBDJ54V5X/graph.json","fetch_events":"https://pith.science/api/pith-number/IV6IQ7MMMTAQ37JBEVBDJ54V5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X/action/storage_attestation","attest_author":"https://pith.science/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X/action/author_attestation","sign_citation":"https://pith.science/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X/action/citation_signature","submit_replication":"https://pith.science/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X/action/replication_record"}},"created_at":"2026-05-18T00:50:12.298702+00:00","updated_at":"2026-05-18T00:50:12.298702+00:00"}