{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6MI6JCWVMZAXLWHMWCPPUTJFMD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3e00aaa12dfa1376897d13e442d5feec64784a825ad21a06a452e0e5d1ec9605","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-21T19:07:50Z","title_canon_sha256":"d8bcc26f49efdd95108be8d37d11fe72bb0c1e1137ec27ab6628a978bbd8d62c"},"schema_version":"1.0","source":{"id":"2204.10374","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.10374","created_at":"2026-07-05T04:16:56Z"},{"alias_kind":"arxiv_version","alias_value":"2204.10374v1","created_at":"2026-07-05T04:16:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.10374","created_at":"2026-07-05T04:16:56Z"},{"alias_kind":"pith_short_12","alias_value":"6MI6JCWVMZAX","created_at":"2026-07-05T04:16:56Z"},{"alias_kind":"pith_short_16","alias_value":"6MI6JCWVMZAXLWHM","created_at":"2026-07-05T04:16:56Z"},{"alias_kind":"pith_short_8","alias_value":"6MI6JCWV","created_at":"2026-07-05T04:16:56Z"}],"graph_snapshots":[{"event_id":"sha256:6a01432da327a254ba57d6fe8968875eca80903560dcdab455053f0798231476","target":"graph","created_at":"2026-07-05T04:16:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2204.10374/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Amelia Glaese, Anita Gergely, Daniel Toyama, Doina Precup, Gheorghe Comanici, Philippe Hamel, Tyler Jackson, Zafarali Ahmed","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-21T19:07:50Z","title":"Learning how to Interact with a Complex Interface using Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.10374","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e5b3ce09519038f7896456010beef16d54294af6ae841ad81ccbd890b8a47413","target":"record","created_at":"2026-07-05T04:16:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3e00aaa12dfa1376897d13e442d5feec64784a825ad21a06a452e0e5d1ec9605","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-21T19:07:50Z","title_canon_sha256":"d8bcc26f49efdd95108be8d37d11fe72bb0c1e1137ec27ab6628a978bbd8d62c"},"schema_version":"1.0","source":{"id":"2204.10374","kind":"arxiv","version":1}},"canonical_sha256":"f311e48ad5664175d8ecb09efa4d2560c646ae81fdc25f0e133e8cc547a6717e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f311e48ad5664175d8ecb09efa4d2560c646ae81fdc25f0e133e8cc547a6717e","first_computed_at":"2026-07-05T04:16:56.137887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:16:56.137887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f8fMN++IALgrjgOVUCM9wd9SBOrDbWCYKIvLc4rnMLOvuGQX28DC9DyOG3qGROBKodY/1MTpDvkms+BkUPvvCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:16:56.138368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.10374","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5b3ce09519038f7896456010beef16d54294af6ae841ad81ccbd890b8a47413","sha256:6a01432da327a254ba57d6fe8968875eca80903560dcdab455053f0798231476"],"state_sha256":"a754007ffaa079789f5206a0b6bde2135db2bec0ceaef9748ebd860ef774aee8"}