{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:YKIS5QQCL5PO3K4EZPB5HOKZMM","short_pith_number":"pith:YKIS5QQC","schema_version":"1.0","canonical_sha256":"c2912ec2025f5eedab84cbc3d3b9596321917eb3a3da140d93ffbc6d7d0c3895","source":{"kind":"arxiv","id":"1705.06769","version":2},"attestation_state":"computed","paper":{"title":"Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Christos Kaplanis, Murray Shanahan, Nat Dilokthanakul, Nick Pawlowski","submitted_at":"2017-05-18T19:00:43Z","abstract_excerpt":"The problem of sparse rewards is one of the hardest challenges in contemporary reinforcement learning. Hierarchical reinforcement learning (HRL) tackles this problem by using a set of temporally-extended actions, or options, each of which has its own subgoal. These subgoals are normally handcrafted for specific tasks. Here, though, we introduce a generic class of subgoals with broad applicability in the visual domain. Underlying our approach (in common with work using \"auxiliary tasks\") is the hypothesis that the ability to control aspects of the environment is an inherently useful skill to ha"},"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":"1705.06769","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-18T19:00:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"38a79dc45c8df85a56d78d81624083240df5f5ffb60559135d1695f9d2ff5810","abstract_canon_sha256":"5f0b788339707f045ec302f549a8c29974316e39a223c917e21bec71fa2c23a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:32:46.251203Z","signature_b64":"FYJzJkBa5l4paLltF3RuHa5QQjesI9Jk1tFBA0oZZ1o1cxQVxFcG7nv0x7FGU1YuaXYwTDcEryGLFKNBXjRPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2912ec2025f5eedab84cbc3d3b9596321917eb3a3da140d93ffbc6d7d0c3895","last_reissued_at":"2026-07-05T00:32:46.250774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:32:46.250774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Christos Kaplanis, Murray Shanahan, Nat Dilokthanakul, Nick Pawlowski","submitted_at":"2017-05-18T19:00:43Z","abstract_excerpt":"The problem of sparse rewards is one of the hardest challenges in contemporary reinforcement learning. Hierarchical reinforcement learning (HRL) tackles this problem by using a set of temporally-extended actions, or options, each of which has its own subgoal. These subgoals are normally handcrafted for specific tasks. Here, though, we introduce a generic class of subgoals with broad applicability in the visual domain. Underlying our approach (in common with work using \"auxiliary tasks\") is the hypothesis that the ability to control aspects of the environment is an inherently useful skill to ha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.06769","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1705.06769/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1705.06769","created_at":"2026-07-05T00:32:46.250840+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.06769v2","created_at":"2026-07-05T00:32:46.250840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.06769","created_at":"2026-07-05T00:32:46.250840+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKIS5QQCL5PO","created_at":"2026-07-05T00:32:46.250840+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKIS5QQCL5PO3K4E","created_at":"2026-07-05T00:32:46.250840+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKIS5QQC","created_at":"2026-07-05T00:32:46.250840+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/YKIS5QQCL5PO3K4EZPB5HOKZMM","json":"https://pith.science/pith/YKIS5QQCL5PO3K4EZPB5HOKZMM.json","graph_json":"https://pith.science/api/pith-number/YKIS5QQCL5PO3K4EZPB5HOKZMM/graph.json","events_json":"https://pith.science/api/pith-number/YKIS5QQCL5PO3K4EZPB5HOKZMM/events.json","paper":"https://pith.science/paper/YKIS5QQC"},"agent_actions":{"view_html":"https://pith.science/pith/YKIS5QQCL5PO3K4EZPB5HOKZMM","download_json":"https://pith.science/pith/YKIS5QQCL5PO3K4EZPB5HOKZMM.json","view_paper":"https://pith.science/paper/YKIS5QQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.06769&json=true","fetch_graph":"https://pith.science/api/pith-number/YKIS5QQCL5PO3K4EZPB5HOKZMM/graph.json","fetch_events":"https://pith.science/api/pith-number/YKIS5QQCL5PO3K4EZPB5HOKZMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKIS5QQCL5PO3K4EZPB5HOKZMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKIS5QQCL5PO3K4EZPB5HOKZMM/action/storage_attestation","attest_author":"https://pith.science/pith/YKIS5QQCL5PO3K4EZPB5HOKZMM/action/author_attestation","sign_citation":"https://pith.science/pith/YKIS5QQCL5PO3K4EZPB5HOKZMM/action/citation_signature","submit_replication":"https://pith.science/pith/YKIS5QQCL5PO3K4EZPB5HOKZMM/action/replication_record"}},"created_at":"2026-07-05T00:32:46.250840+00:00","updated_at":"2026-07-05T00:32:46.250840+00:00"}