{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:G2A6TALSGL3DBPTDSX2QN7BB7E","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":"582db74d995dea5cffb0d902127ce69f1cc5abd58f31356d6fd131be5a341b5a","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-04T22:46:16Z","title_canon_sha256":"071425454f6090574d5432e742b44f0a3865d497dc46d968364996e323a82131"},"schema_version":"1.0","source":{"id":"2111.03189","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.03189","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2111.03189v2","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03189","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"G2A6TALSGL3D","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"G2A6TALSGL3DBPTD","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"G2A6TALS","created_at":"2026-07-05T04:09:59Z"}],"graph_snapshots":[{"event_id":"sha256:6b201eaea50f288dca3c1572348e958c5fa737905a09d63aac05a3da5a5e9aa6","target":"graph","created_at":"2026-07-05T04:09:59Z","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/2111.03189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning can train policies that effectively perform complex tasks. However for long-horizon tasks, the performance of these methods degrades with horizon, often necessitating reasoning over and chaining lower-level skills. Hierarchical reinforcement learning aims to enable this by providing a bank of low-level skills as action abstractions. Hierarchies can further improve on this by abstracting the space states as well. We posit that a suitable state abstraction should depend on the capabilities of the available lower-level policies. We propose Value Function Spaces: a simple ap","authors_text":"Alexander Toshev, Brian Ichter, Dhruv Shah, Peng Xu, Sergey Levine, Ted Xiao, Yao Lu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-04T22:46:16Z","title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03189","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":"sha256:61aeb810f18a94b12872e306f85219dd765a59178e8f67d43fa0145e22738904","target":"record","created_at":"2026-07-05T04:09:59Z","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":"582db74d995dea5cffb0d902127ce69f1cc5abd58f31356d6fd131be5a341b5a","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-04T22:46:16Z","title_canon_sha256":"071425454f6090574d5432e742b44f0a3865d497dc46d968364996e323a82131"},"schema_version":"1.0","source":{"id":"2111.03189","kind":"arxiv","version":2}},"canonical_sha256":"3681e9817232f630be6395f506fc21f901058e66ef99548e97d8b7b4876cafc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3681e9817232f630be6395f506fc21f901058e66ef99548e97d8b7b4876cafc0","first_computed_at":"2026-07-05T04:09:59.027013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:59.027013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TmvotIDaKQ0AkblkNwXbRX+9LVMs5OukJVlvFgj1yq/upUMhDRTZDUBMpwIQq23U9Z2LwadGHdlmBlcYqIlhCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:59.027487Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.03189","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61aeb810f18a94b12872e306f85219dd765a59178e8f67d43fa0145e22738904","sha256:6b201eaea50f288dca3c1572348e958c5fa737905a09d63aac05a3da5a5e9aa6"],"state_sha256":"17718df4e3b7a736253d4c43da4862293311cf27a9fd531ae37ae1be64ba9fee"}