{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ZF46TWEF4HSSOZTPF42CCPRHEO","short_pith_number":"pith:ZF46TWEF","schema_version":"1.0","canonical_sha256":"c979e9d885e1e527666f2f34213e27238a1234370de9aa48e20188d100280484","source":{"kind":"arxiv","id":"1604.08153","version":3},"attestation_state":"computed","paper":{"title":"Classifying Options for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anil Anthony Bharath, Kai Arulkumaran, Murray Shanahan, Nat Dilokthanakul","submitted_at":"2016-04-27T17:48:39Z","abstract_excerpt":"In this paper we combine one method for hierarchical reinforcement learning - the options framework - with deep Q-networks (DQNs) through the use of different \"option heads\" on the policy network, and a supervisory network for choosing between the different options. We utilise our setup to investigate the effects of architectural constraints in subtasks with positive and negative transfer, across a range of network capacities. We empirically show that our augmented DQN has lower sample complexity when simultaneously learning subtasks with negative transfer, without degrading performance when l"},"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":"1604.08153","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-27T17:48:39Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"7e74d94fbc693537ec317340505f22b70829bc7d4dc6a736058504f614c4a1bb","abstract_canon_sha256":"5f36927a03e0bb6b24ad447747bbb8041860b4ec0b4f449b3d64f4e1b9b5366a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:13.112751Z","signature_b64":"KBev79FnR/+PHiIpXUYkCPjaxQDOoNQm56iA4rlUgrpbCtP6PpB/y8nAA8jwJVyJb0yWjdX1Skdg/gJeUvXlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c979e9d885e1e527666f2f34213e27238a1234370de9aa48e20188d100280484","last_reissued_at":"2026-05-18T00:42:13.112109Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:13.112109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Classifying Options for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anil Anthony Bharath, Kai Arulkumaran, Murray Shanahan, Nat Dilokthanakul","submitted_at":"2016-04-27T17:48:39Z","abstract_excerpt":"In this paper we combine one method for hierarchical reinforcement learning - the options framework - with deep Q-networks (DQNs) through the use of different \"option heads\" on the policy network, and a supervisory network for choosing between the different options. We utilise our setup to investigate the effects of architectural constraints in subtasks with positive and negative transfer, across a range of network capacities. We empirically show that our augmented DQN has lower sample complexity when simultaneously learning subtasks with negative transfer, without degrading performance when l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.08153","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":"1604.08153","created_at":"2026-05-18T00:42:13.112203+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.08153v3","created_at":"2026-05-18T00:42:13.112203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.08153","created_at":"2026-05-18T00:42:13.112203+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZF46TWEF4HSS","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZF46TWEF4HSSOZTP","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZF46TWEF","created_at":"2026-05-18T12:30:53.716459+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/ZF46TWEF4HSSOZTPF42CCPRHEO","json":"https://pith.science/pith/ZF46TWEF4HSSOZTPF42CCPRHEO.json","graph_json":"https://pith.science/api/pith-number/ZF46TWEF4HSSOZTPF42CCPRHEO/graph.json","events_json":"https://pith.science/api/pith-number/ZF46TWEF4HSSOZTPF42CCPRHEO/events.json","paper":"https://pith.science/paper/ZF46TWEF"},"agent_actions":{"view_html":"https://pith.science/pith/ZF46TWEF4HSSOZTPF42CCPRHEO","download_json":"https://pith.science/pith/ZF46TWEF4HSSOZTPF42CCPRHEO.json","view_paper":"https://pith.science/paper/ZF46TWEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.08153&json=true","fetch_graph":"https://pith.science/api/pith-number/ZF46TWEF4HSSOZTPF42CCPRHEO/graph.json","fetch_events":"https://pith.science/api/pith-number/ZF46TWEF4HSSOZTPF42CCPRHEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZF46TWEF4HSSOZTPF42CCPRHEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZF46TWEF4HSSOZTPF42CCPRHEO/action/storage_attestation","attest_author":"https://pith.science/pith/ZF46TWEF4HSSOZTPF42CCPRHEO/action/author_attestation","sign_citation":"https://pith.science/pith/ZF46TWEF4HSSOZTPF42CCPRHEO/action/citation_signature","submit_replication":"https://pith.science/pith/ZF46TWEF4HSSOZTPF42CCPRHEO/action/replication_record"}},"created_at":"2026-05-18T00:42:13.112203+00:00","updated_at":"2026-05-18T00:42:13.112203+00:00"}