{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WKESWXSX45YOAXTXVHNVZB7PGE","short_pith_number":"pith:WKESWXSX","schema_version":"1.0","canonical_sha256":"b2892b5e57e770e05e77a9db5c87ef310b525dfe276af86c951ac088eae6c61d","source":{"kind":"arxiv","id":"2409.08724","version":1},"attestation_state":"computed","paper":{"title":"Quasimetric Value Functions with Dense Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bikramjit Banerjee, Khadichabonu Valieva","submitted_at":"2024-09-13T11:26:05Z","abstract_excerpt":"As a generalization of reinforcement learning (RL) to parametrizable goals, goal conditioned RL (GCRL) has a broad range of applications, particularly in challenging tasks in robotics. Recent work has established that the optimal value function of GCRL $Q^\\ast(s,a,g)$ has a quasimetric structure, leading to targetted neural architectures that respect such structure. However, the relevant analyses assume a sparse reward setting -- a known aggravating factor to sample complexity. We show that the key property underpinning a quasimetric, viz., the triangle inequality, is preserved under a dense r"},"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":"2409.08724","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-13T11:26:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2633b1368a307fefc3bf94633e45ab1437894341fb668a2ebd765a0d9e17ff5a","abstract_canon_sha256":"1fcab673c7fa2534ab2264130928f0c58a694365961761bc37235c2763aff41e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:46.187888Z","signature_b64":"p1MNVjQs8Qztu6cwa0NDamlcUsO+tZgxH7Yx9+y0CWsRwqOyuzPZFEHfF4GMoRAYradUWCZ/EjJz5i/Mu1HvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2892b5e57e770e05e77a9db5c87ef310b525dfe276af86c951ac088eae6c61d","last_reissued_at":"2026-07-05T09:06:46.187478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:46.187478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quasimetric Value Functions with Dense Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bikramjit Banerjee, Khadichabonu Valieva","submitted_at":"2024-09-13T11:26:05Z","abstract_excerpt":"As a generalization of reinforcement learning (RL) to parametrizable goals, goal conditioned RL (GCRL) has a broad range of applications, particularly in challenging tasks in robotics. Recent work has established that the optimal value function of GCRL $Q^\\ast(s,a,g)$ has a quasimetric structure, leading to targetted neural architectures that respect such structure. However, the relevant analyses assume a sparse reward setting -- a known aggravating factor to sample complexity. We show that the key property underpinning a quasimetric, viz., the triangle inequality, is preserved under a dense r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08724","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/2409.08724/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":"2409.08724","created_at":"2026-07-05T09:06:46.187530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08724v1","created_at":"2026-07-05T09:06:46.187530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08724","created_at":"2026-07-05T09:06:46.187530+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKESWXSX45YO","created_at":"2026-07-05T09:06:46.187530+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKESWXSX45YOAXTX","created_at":"2026-07-05T09:06:46.187530+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKESWXSX","created_at":"2026-07-05T09:06:46.187530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.08902","citing_title":"Intention-Conditioned Flow Occupancy Models","ref_index":117,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKESWXSX45YOAXTXVHNVZB7PGE","json":"https://pith.science/pith/WKESWXSX45YOAXTXVHNVZB7PGE.json","graph_json":"https://pith.science/api/pith-number/WKESWXSX45YOAXTXVHNVZB7PGE/graph.json","events_json":"https://pith.science/api/pith-number/WKESWXSX45YOAXTXVHNVZB7PGE/events.json","paper":"https://pith.science/paper/WKESWXSX"},"agent_actions":{"view_html":"https://pith.science/pith/WKESWXSX45YOAXTXVHNVZB7PGE","download_json":"https://pith.science/pith/WKESWXSX45YOAXTXVHNVZB7PGE.json","view_paper":"https://pith.science/paper/WKESWXSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08724&json=true","fetch_graph":"https://pith.science/api/pith-number/WKESWXSX45YOAXTXVHNVZB7PGE/graph.json","fetch_events":"https://pith.science/api/pith-number/WKESWXSX45YOAXTXVHNVZB7PGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKESWXSX45YOAXTXVHNVZB7PGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKESWXSX45YOAXTXVHNVZB7PGE/action/storage_attestation","attest_author":"https://pith.science/pith/WKESWXSX45YOAXTXVHNVZB7PGE/action/author_attestation","sign_citation":"https://pith.science/pith/WKESWXSX45YOAXTXVHNVZB7PGE/action/citation_signature","submit_replication":"https://pith.science/pith/WKESWXSX45YOAXTXVHNVZB7PGE/action/replication_record"}},"created_at":"2026-07-05T09:06:46.187530+00:00","updated_at":"2026-07-05T09:06:46.187530+00:00"}