{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F6Y4WTH3JET7DK23TTPJZRNW6L","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":"f970e590d7705eef12f589b108783f54cc5c30482c7c1e3566d6d821e6a4ac90","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T17:09:26Z","title_canon_sha256":"e42eaa3d71bd8bf916d46f18a5f9a4bd727e7bf9d2aeae8149bfaca69d8f494b"},"schema_version":"1.0","source":{"id":"2410.08997","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08997","created_at":"2026-07-05T09:26:31Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08997v2","created_at":"2026-07-05T09:26:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08997","created_at":"2026-07-05T09:26:31Z"},{"alias_kind":"pith_short_12","alias_value":"F6Y4WTH3JET7","created_at":"2026-07-05T09:26:31Z"},{"alias_kind":"pith_short_16","alias_value":"F6Y4WTH3JET7DK23","created_at":"2026-07-05T09:26:31Z"},{"alias_kind":"pith_short_8","alias_value":"F6Y4WTH3","created_at":"2026-07-05T09:26:31Z"}],"graph_snapshots":[{"event_id":"sha256:6c3e9fd16e23bc7f61c2d2cfbe562d0a342dbde315cc9de00fd20077f20a50db","target":"graph","created_at":"2026-07-05T09:26:31Z","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/2410.08997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There have been key advancements to building universal approximators for multi-goal collections of reinforcement learning value functions -- key elements in estimating long-term returns of states in a parameterized manner. We extend this to hierarchical reinforcement learning, using the options framework, by introducing hierarchical universal value function approximators (H-UVFAs). This allows us to leverage the added benefits of scaling, planning, and generalization expected in temporal abstraction settings. We develop supervised and reinforcement learning methods for learning embeddings of t","authors_text":"Rushiv Arora","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T17:09:26Z","title":"Hierarchical Universal Value Function Approximators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08997","kind":"arxiv","version":2},"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":"sha256:3f2761b04715fcb4cca6700eff74c03133e4a08bee2ff190b6fe499e3811a907","target":"record","created_at":"2026-07-05T09:26:31Z","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":"f970e590d7705eef12f589b108783f54cc5c30482c7c1e3566d6d821e6a4ac90","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T17:09:26Z","title_canon_sha256":"e42eaa3d71bd8bf916d46f18a5f9a4bd727e7bf9d2aeae8149bfaca69d8f494b"},"schema_version":"1.0","source":{"id":"2410.08997","kind":"arxiv","version":2}},"canonical_sha256":"2fb1cb4cfb4927f1ab5b9cde9cc5b6f2c3534e4be63337115b6914b4cd9cfa75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fb1cb4cfb4927f1ab5b9cde9cc5b6f2c3534e4be63337115b6914b4cd9cfa75","first_computed_at":"2026-07-05T09:26:31.070824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:31.070824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DtkxZVEEh3zFR7qRjF/L8pioP5MLa5l2qRfoT+JwF8eCQ3KvhMYApLek/DSOwjx/b+OPQH1whvE1lz0eoi7oAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:31.071293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08997","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f2761b04715fcb4cca6700eff74c03133e4a08bee2ff190b6fe499e3811a907","sha256:6c3e9fd16e23bc7f61c2d2cfbe562d0a342dbde315cc9de00fd20077f20a50db"],"state_sha256":"cf4d07f53172fd63329bef30f5bb0d2d8f94db12dc8a432b979a33c1e6ae6841"}