{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:E6CSMY3KHOKUNBCNFGQQE3DXRS","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":"8f6c5e097af6420d5826740933fb11f1824143b186d1a34ef42071659552fa2a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-04-02T16:41:17Z","title_canon_sha256":"d60dfcb60e2500d1fc5697aa2de2f3cecce21911e610c9d5eb5297a5d7ba80aa"},"schema_version":"1.0","source":{"id":"2204.00898","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00898","created_at":"2026-07-05T04:28:54Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00898v3","created_at":"2026-07-05T04:28:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00898","created_at":"2026-07-05T04:28:54Z"},{"alias_kind":"pith_short_12","alias_value":"E6CSMY3KHOKU","created_at":"2026-07-05T04:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"E6CSMY3KHOKUNBCN","created_at":"2026-07-05T04:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"E6CSMY3K","created_at":"2026-07-05T04:28:54Z"}],"graph_snapshots":[{"event_id":"sha256:fa5d8dfd53bc1322a32da8c7fd88327e2b7facd6c6d3936434fdd0c51bdc66e5","target":"graph","created_at":"2026-07-05T04:28:54Z","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/2204.00898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The framework of mixed observable Markov decision processes (MOMDP) models many robotic domains in which some state variables are fully observable while others are not. In this work, we identify a significant subclass of MOMDPs defined by how actions influence the fully observable components of the state and how those, in turn, influence the partially observable components and the rewards. This unique property allows for a two-level hierarchical approach we call HIerarchical Reinforcement Learning under Mixed Observability (HILMO), which restricts partial observability to the top level while t","authors_text":"Andrea Baisero, Christopher Amato, Hai Nguyen, Robert Platt, Xiao Ma, Zhihan Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-04-02T16:41:17Z","title":"Hierarchical Reinforcement Learning under Mixed Observability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00898","kind":"arxiv","version":3},"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:ef1fd1c2dbd51c9599c6a54414019026a8e8571dbc2285d6bcaed59d5df2e645","target":"record","created_at":"2026-07-05T04:28:54Z","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":"8f6c5e097af6420d5826740933fb11f1824143b186d1a34ef42071659552fa2a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-04-02T16:41:17Z","title_canon_sha256":"d60dfcb60e2500d1fc5697aa2de2f3cecce21911e610c9d5eb5297a5d7ba80aa"},"schema_version":"1.0","source":{"id":"2204.00898","kind":"arxiv","version":3}},"canonical_sha256":"278526636a3b9546844d29a1026c778c875c43644d2a5dcfe2fec281e4b98af8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"278526636a3b9546844d29a1026c778c875c43644d2a5dcfe2fec281e4b98af8","first_computed_at":"2026-07-05T04:28:54.704955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:28:54.704955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JV/OJZHPVWIHBQHtN3bPo3ci2Vdrey2uCbCnYlKcUJImm0y+DoyJA3KCMpWX/TM6rZNutUdtKIOF6hsrXVYbAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:28:54.705491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.00898","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef1fd1c2dbd51c9599c6a54414019026a8e8571dbc2285d6bcaed59d5df2e645","sha256:fa5d8dfd53bc1322a32da8c7fd88327e2b7facd6c6d3936434fdd0c51bdc66e5"],"state_sha256":"54b4f8c97387ee7c8d7ec8b3221b2a0bc6e9e1509aecf4cc34489a9b6cbbc4be"}