{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6MI6JCWVMZAXLWHMWCPPUTJFMD","short_pith_number":"pith:6MI6JCWV","schema_version":"1.0","canonical_sha256":"f311e48ad5664175d8ecb09efa4d2560c646ae81fdc25f0e133e8cc547a6717e","source":{"kind":"arxiv","id":"2204.10374","version":1},"attestation_state":"computed","paper":{"title":"Learning how to Interact with a Complex Interface using Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amelia Glaese, Anita Gergely, Daniel Toyama, Doina Precup, Gheorghe Comanici, Philippe Hamel, Tyler Jackson, Zafarali Ahmed","submitted_at":"2022-04-21T19:07:50Z","abstract_excerpt":"Hierarchical Reinforcement Learning (HRL) allows interactive agents to decompose complex problems into a hierarchy of sub-tasks. Higher-level tasks can invoke the solutions of lower-level tasks as if they were primitive actions. In this work, we study the utility of hierarchical decompositions for learning an appropriate way to interact with a complex interface. Specifically, we train HRL agents that can interface with applications in a simulated Android device. We introduce a Hierarchical Distributed Deep Reinforcement Learning architecture that learns (1) subtasks corresponding to simple fin"},"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":"2204.10374","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-21T19:07:50Z","cross_cats_sorted":[],"title_canon_sha256":"d8bcc26f49efdd95108be8d37d11fe72bb0c1e1137ec27ab6628a978bbd8d62c","abstract_canon_sha256":"3e00aaa12dfa1376897d13e442d5feec64784a825ad21a06a452e0e5d1ec9605"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:56.138368Z","signature_b64":"f8fMN++IALgrjgOVUCM9wd9SBOrDbWCYKIvLc4rnMLOvuGQX28DC9DyOG3qGROBKodY/1MTpDvkms+BkUPvvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f311e48ad5664175d8ecb09efa4d2560c646ae81fdc25f0e133e8cc547a6717e","last_reissued_at":"2026-07-05T04:16:56.137887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:56.137887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning how to Interact with a Complex Interface using Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amelia Glaese, Anita Gergely, Daniel Toyama, Doina Precup, Gheorghe Comanici, Philippe Hamel, Tyler Jackson, Zafarali Ahmed","submitted_at":"2022-04-21T19:07:50Z","abstract_excerpt":"Hierarchical Reinforcement Learning (HRL) allows interactive agents to decompose complex problems into a hierarchy of sub-tasks. Higher-level tasks can invoke the solutions of lower-level tasks as if they were primitive actions. In this work, we study the utility of hierarchical decompositions for learning an appropriate way to interact with a complex interface. Specifically, we train HRL agents that can interface with applications in a simulated Android device. We introduce a Hierarchical Distributed Deep Reinforcement Learning architecture that learns (1) subtasks corresponding to simple fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.10374","kind":"arxiv","version":1},"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/2204.10374/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":"2204.10374","created_at":"2026-07-05T04:16:56.137942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.10374v1","created_at":"2026-07-05T04:16:56.137942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.10374","created_at":"2026-07-05T04:16:56.137942+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MI6JCWVMZAX","created_at":"2026-07-05T04:16:56.137942+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MI6JCWVMZAXLWHM","created_at":"2026-07-05T04:16:56.137942+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MI6JCWV","created_at":"2026-07-05T04:16:56.137942+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16983","citing_title":"Hierarchical Reinforcement Learning Framework for Adaptive Walking Control Using General Value Functions of Lower-Limb Sensor Signals","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MI6JCWVMZAXLWHMWCPPUTJFMD","json":"https://pith.science/pith/6MI6JCWVMZAXLWHMWCPPUTJFMD.json","graph_json":"https://pith.science/api/pith-number/6MI6JCWVMZAXLWHMWCPPUTJFMD/graph.json","events_json":"https://pith.science/api/pith-number/6MI6JCWVMZAXLWHMWCPPUTJFMD/events.json","paper":"https://pith.science/paper/6MI6JCWV"},"agent_actions":{"view_html":"https://pith.science/pith/6MI6JCWVMZAXLWHMWCPPUTJFMD","download_json":"https://pith.science/pith/6MI6JCWVMZAXLWHMWCPPUTJFMD.json","view_paper":"https://pith.science/paper/6MI6JCWV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.10374&json=true","fetch_graph":"https://pith.science/api/pith-number/6MI6JCWVMZAXLWHMWCPPUTJFMD/graph.json","fetch_events":"https://pith.science/api/pith-number/6MI6JCWVMZAXLWHMWCPPUTJFMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MI6JCWVMZAXLWHMWCPPUTJFMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MI6JCWVMZAXLWHMWCPPUTJFMD/action/storage_attestation","attest_author":"https://pith.science/pith/6MI6JCWVMZAXLWHMWCPPUTJFMD/action/author_attestation","sign_citation":"https://pith.science/pith/6MI6JCWVMZAXLWHMWCPPUTJFMD/action/citation_signature","submit_replication":"https://pith.science/pith/6MI6JCWVMZAXLWHMWCPPUTJFMD/action/replication_record"}},"created_at":"2026-07-05T04:16:56.137942+00:00","updated_at":"2026-07-05T04:16:56.137942+00:00"}