{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:G2A6TALSGL3DBPTDSX2QN7BB7E","short_pith_number":"pith:G2A6TALS","schema_version":"1.0","canonical_sha256":"3681e9817232f630be6395f506fc21f901058e66ef99548e97d8b7b4876cafc0","source":{"kind":"arxiv","id":"2111.03189","version":2},"attestation_state":"computed","paper":{"title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Alexander Toshev, Brian Ichter, Dhruv Shah, Peng Xu, Sergey Levine, Ted Xiao, Yao Lu","submitted_at":"2021-11-04T22:46:16Z","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"},"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":"2111.03189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-04T22:46:16Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"071425454f6090574d5432e742b44f0a3865d497dc46d968364996e323a82131","abstract_canon_sha256":"582db74d995dea5cffb0d902127ce69f1cc5abd58f31356d6fd131be5a341b5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:59.027487Z","signature_b64":"TmvotIDaKQ0AkblkNwXbRX+9LVMs5OukJVlvFgj1yq/upUMhDRTZDUBMpwIQq23U9Z2LwadGHdlmBlcYqIlhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3681e9817232f630be6395f506fc21f901058e66ef99548e97d8b7b4876cafc0","last_reissued_at":"2026-07-05T04:09:59.027013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:59.027013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Alexander Toshev, Brian Ichter, Dhruv Shah, Peng Xu, Sergey Levine, Ted Xiao, Yao Lu","submitted_at":"2021-11-04T22:46:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03189","kind":"arxiv","version":2},"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/2111.03189/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":"2111.03189","created_at":"2026-07-05T04:09:59.027070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.03189v2","created_at":"2026-07-05T04:09:59.027070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03189","created_at":"2026-07-05T04:09:59.027070+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2A6TALSGL3D","created_at":"2026-07-05T04:09:59.027070+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2A6TALSGL3DBPTD","created_at":"2026-07-05T04:09:59.027070+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2A6TALS","created_at":"2026-07-05T04:09:59.027070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2204.01691","citing_title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G2A6TALSGL3DBPTDSX2QN7BB7E","json":"https://pith.science/pith/G2A6TALSGL3DBPTDSX2QN7BB7E.json","graph_json":"https://pith.science/api/pith-number/G2A6TALSGL3DBPTDSX2QN7BB7E/graph.json","events_json":"https://pith.science/api/pith-number/G2A6TALSGL3DBPTDSX2QN7BB7E/events.json","paper":"https://pith.science/paper/G2A6TALS"},"agent_actions":{"view_html":"https://pith.science/pith/G2A6TALSGL3DBPTDSX2QN7BB7E","download_json":"https://pith.science/pith/G2A6TALSGL3DBPTDSX2QN7BB7E.json","view_paper":"https://pith.science/paper/G2A6TALS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.03189&json=true","fetch_graph":"https://pith.science/api/pith-number/G2A6TALSGL3DBPTDSX2QN7BB7E/graph.json","fetch_events":"https://pith.science/api/pith-number/G2A6TALSGL3DBPTDSX2QN7BB7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2A6TALSGL3DBPTDSX2QN7BB7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2A6TALSGL3DBPTDSX2QN7BB7E/action/storage_attestation","attest_author":"https://pith.science/pith/G2A6TALSGL3DBPTDSX2QN7BB7E/action/author_attestation","sign_citation":"https://pith.science/pith/G2A6TALSGL3DBPTDSX2QN7BB7E/action/citation_signature","submit_replication":"https://pith.science/pith/G2A6TALSGL3DBPTDSX2QN7BB7E/action/replication_record"}},"created_at":"2026-07-05T04:09:59.027070+00:00","updated_at":"2026-07-05T04:09:59.027070+00:00"}