{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:VONYAEIXI7Y2DKSADDCWSUL2HO","short_pith_number":"pith:VONYAEIX","schema_version":"1.0","canonical_sha256":"ab9b80111747f1a1aa4018c569517a3ba68e6e0fffca123c717625616f0d4d4e","source":{"kind":"arxiv","id":"1604.06057","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ardavan Saeedi, Joshua B. Tenenbaum, Karthik R. Narasimhan, Tejas D. Kulkarni","submitted_at":"2016-04-20T18:47:48Z","abstract_excerpt":"Learning goal-directed behavior in environments with sparse feedback is a major challenge for reinforcement learning algorithms. The primary difficulty arises due to insufficient exploration, resulting in an agent being unable to learn robust value functions. Intrinsically motivated agents can explore new behavior for its own sake rather than to directly solve problems. Such intrinsic behaviors could eventually help the agent solve tasks posed by the environment. We present hierarchical-DQN (h-DQN), a framework to integrate hierarchical value functions, operating at different temporal scales, "},"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":"1604.06057","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-20T18:47:48Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"1b2663fc291a7db8c2482dab007e9b02d11f15708f58719f088c44d54d59a705","abstract_canon_sha256":"6a56db752b04c3965a2f7f7b3c8caf8dd8267426941e44d8a441a254d07f50f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:11.062869Z","signature_b64":"tIBGwyl77vPBViTtvuOmSxs8PFxJp8Y5frD16G0X7VHZ7UPgBQupHiXe+MlphTjxwA9y9ij1AjOb6PF5XIiKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab9b80111747f1a1aa4018c569517a3ba68e6e0fffca123c717625616f0d4d4e","last_reissued_at":"2026-05-18T01:13:11.062513Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:11.062513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ardavan Saeedi, Joshua B. Tenenbaum, Karthik R. Narasimhan, Tejas D. Kulkarni","submitted_at":"2016-04-20T18:47:48Z","abstract_excerpt":"Learning goal-directed behavior in environments with sparse feedback is a major challenge for reinforcement learning algorithms. The primary difficulty arises due to insufficient exploration, resulting in an agent being unable to learn robust value functions. Intrinsically motivated agents can explore new behavior for its own sake rather than to directly solve problems. Such intrinsic behaviors could eventually help the agent solve tasks posed by the environment. We present hierarchical-DQN (h-DQN), a framework to integrate hierarchical value functions, operating at different temporal scales, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.06057","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":"1604.06057","created_at":"2026-05-18T01:13:11.062569+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.06057v2","created_at":"2026-05-18T01:13:11.062569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.06057","created_at":"2026-05-18T01:13:11.062569+00:00"},{"alias_kind":"pith_short_12","alias_value":"VONYAEIXI7Y2","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_16","alias_value":"VONYAEIXI7Y2DKSA","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_8","alias_value":"VONYAEIX","created_at":"2026-05-18T12:30:48.956258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2601.09726","citing_title":"Forgetting as a Feature: Cognitive Alignment of Large Language Models","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"1606.06565","citing_title":"Concrete Problems in AI Safety","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VONYAEIXI7Y2DKSADDCWSUL2HO","json":"https://pith.science/pith/VONYAEIXI7Y2DKSADDCWSUL2HO.json","graph_json":"https://pith.science/api/pith-number/VONYAEIXI7Y2DKSADDCWSUL2HO/graph.json","events_json":"https://pith.science/api/pith-number/VONYAEIXI7Y2DKSADDCWSUL2HO/events.json","paper":"https://pith.science/paper/VONYAEIX"},"agent_actions":{"view_html":"https://pith.science/pith/VONYAEIXI7Y2DKSADDCWSUL2HO","download_json":"https://pith.science/pith/VONYAEIXI7Y2DKSADDCWSUL2HO.json","view_paper":"https://pith.science/paper/VONYAEIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.06057&json=true","fetch_graph":"https://pith.science/api/pith-number/VONYAEIXI7Y2DKSADDCWSUL2HO/graph.json","fetch_events":"https://pith.science/api/pith-number/VONYAEIXI7Y2DKSADDCWSUL2HO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VONYAEIXI7Y2DKSADDCWSUL2HO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VONYAEIXI7Y2DKSADDCWSUL2HO/action/storage_attestation","attest_author":"https://pith.science/pith/VONYAEIXI7Y2DKSADDCWSUL2HO/action/author_attestation","sign_citation":"https://pith.science/pith/VONYAEIXI7Y2DKSADDCWSUL2HO/action/citation_signature","submit_replication":"https://pith.science/pith/VONYAEIXI7Y2DKSADDCWSUL2HO/action/replication_record"}},"created_at":"2026-05-18T01:13:11.062569+00:00","updated_at":"2026-05-18T01:13:11.062569+00:00"}