{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WX5S25GQN7VLID5D2LRKNW6DW6","short_pith_number":"pith:WX5S25GQ","schema_version":"1.0","canonical_sha256":"b5fb2d74d06feab40fa3d2e2a6dbc3b79fb4fb935c4eb9a4de2b782d9d68e1d0","source":{"kind":"arxiv","id":"2505.21750","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Joni Pajarinen, Tinghuai Wang, Vivienne Huiling Wang","submitted_at":"2025-05-27T20:38:44Z","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 "},"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":"2505.21750","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T20:38:44Z","cross_cats_sorted":[],"title_canon_sha256":"edc3ddfbeae13c502c0011b7684ec52ce5232498e4c2ad5a927853c598e93202","abstract_canon_sha256":"962a44105eff317fe996dcf13783a1da106bbbea89d6fa28bb8a199acdcc6082"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:02.984008Z","signature_b64":"MlYWc52kB1FwV4LCNDQFmM0vXCjzdrpUuI9GOh0lwwxJrQwaeCZq7m2NzxIMuZw+qhxnImjjjNDC/QOMJ5Q5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5fb2d74d06feab40fa3d2e2a6dbc3b79fb4fb935c4eb9a4de2b782d9d68e1d0","last_reissued_at":"2026-07-05T11:11:02.983485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:02.983485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Joni Pajarinen, Tinghuai Wang, Vivienne Huiling Wang","submitted_at":"2025-05-27T20:38:44Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21750","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/2505.21750/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":"2505.21750","created_at":"2026-07-05T11:11:02.983544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21750v1","created_at":"2026-07-05T11:11:02.983544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21750","created_at":"2026-07-05T11:11:02.983544+00:00"},{"alias_kind":"pith_short_12","alias_value":"WX5S25GQN7VL","created_at":"2026-07-05T11:11:02.983544+00:00"},{"alias_kind":"pith_short_16","alias_value":"WX5S25GQN7VLID5D","created_at":"2026-07-05T11:11:02.983544+00:00"},{"alias_kind":"pith_short_8","alias_value":"WX5S25GQ","created_at":"2026-07-05T11:11:02.983544+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/WX5S25GQN7VLID5D2LRKNW6DW6","json":"https://pith.science/pith/WX5S25GQN7VLID5D2LRKNW6DW6.json","graph_json":"https://pith.science/api/pith-number/WX5S25GQN7VLID5D2LRKNW6DW6/graph.json","events_json":"https://pith.science/api/pith-number/WX5S25GQN7VLID5D2LRKNW6DW6/events.json","paper":"https://pith.science/paper/WX5S25GQ"},"agent_actions":{"view_html":"https://pith.science/pith/WX5S25GQN7VLID5D2LRKNW6DW6","download_json":"https://pith.science/pith/WX5S25GQN7VLID5D2LRKNW6DW6.json","view_paper":"https://pith.science/paper/WX5S25GQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21750&json=true","fetch_graph":"https://pith.science/api/pith-number/WX5S25GQN7VLID5D2LRKNW6DW6/graph.json","fetch_events":"https://pith.science/api/pith-number/WX5S25GQN7VLID5D2LRKNW6DW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WX5S25GQN7VLID5D2LRKNW6DW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WX5S25GQN7VLID5D2LRKNW6DW6/action/storage_attestation","attest_author":"https://pith.science/pith/WX5S25GQN7VLID5D2LRKNW6DW6/action/author_attestation","sign_citation":"https://pith.science/pith/WX5S25GQN7VLID5D2LRKNW6DW6/action/citation_signature","submit_replication":"https://pith.science/pith/WX5S25GQN7VLID5D2LRKNW6DW6/action/replication_record"}},"created_at":"2026-07-05T11:11:02.983544+00:00","updated_at":"2026-07-05T11:11:02.983544+00:00"}