{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WX5S25GQN7VLID5D2LRKNW6DW6","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":"962a44105eff317fe996dcf13783a1da106bbbea89d6fa28bb8a199acdcc6082","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T20:38:44Z","title_canon_sha256":"edc3ddfbeae13c502c0011b7684ec52ce5232498e4c2ad5a927853c598e93202"},"schema_version":"1.0","source":{"id":"2505.21750","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21750","created_at":"2026-07-05T11:11:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21750v1","created_at":"2026-07-05T11:11:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21750","created_at":"2026-07-05T11:11:02Z"},{"alias_kind":"pith_short_12","alias_value":"WX5S25GQN7VL","created_at":"2026-07-05T11:11:02Z"},{"alias_kind":"pith_short_16","alias_value":"WX5S25GQN7VLID5D","created_at":"2026-07-05T11:11:02Z"},{"alias_kind":"pith_short_8","alias_value":"WX5S25GQ","created_at":"2026-07-05T11:11:02Z"}],"graph_snapshots":[{"event_id":"sha256:726e69261dde8dfa72fa8542d5e436607e2cc7a359e9427cfa0422056bf6863d","target":"graph","created_at":"2026-07-05T11:11:02Z","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/2505.21750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hierarchical reinforcement learning (HRL) learns to make decisions on multiple levels of temporal abstraction. A key challenge in HRL is that the low-level policy changes over time, making it difficult for the high-level policy to generate effective subgoals. To address this issue, the high-level policy must capture a complex subgoal distribution while also accounting for uncertainty in its estimates. We propose an approach that trains a conditional diffusion model regularized by a Gaussian Process (GP) prior to generate a complex variety of subgoals while leveraging principled GP uncertainty ","authors_text":"Joni Pajarinen, Tinghuai Wang, Vivienne Huiling Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T20:38:44Z","title":"Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21750","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":"sha256:51f7cee283fe54277fea2ba16d5afec280842d1f5812840b1174076a89da6c63","target":"record","created_at":"2026-07-05T11:11:02Z","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":"962a44105eff317fe996dcf13783a1da106bbbea89d6fa28bb8a199acdcc6082","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T20:38:44Z","title_canon_sha256":"edc3ddfbeae13c502c0011b7684ec52ce5232498e4c2ad5a927853c598e93202"},"schema_version":"1.0","source":{"id":"2505.21750","kind":"arxiv","version":1}},"canonical_sha256":"b5fb2d74d06feab40fa3d2e2a6dbc3b79fb4fb935c4eb9a4de2b782d9d68e1d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5fb2d74d06feab40fa3d2e2a6dbc3b79fb4fb935c4eb9a4de2b782d9d68e1d0","first_computed_at":"2026-07-05T11:11:02.983485Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:02.983485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MlYWc52kB1FwV4LCNDQFmM0vXCjzdrpUuI9GOh0lwwxJrQwaeCZq7m2NzxIMuZw+qhxnImjjjNDC/QOMJ5Q5DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:02.984008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21750","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51f7cee283fe54277fea2ba16d5afec280842d1f5812840b1174076a89da6c63","sha256:726e69261dde8dfa72fa8542d5e436607e2cc7a359e9427cfa0422056bf6863d"],"state_sha256":"23853c1b384640fbf6f56984719166bdf073fea34a30c489931e03050b3acb57"}