{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YAVWVMMO4IVGXRUWAN3PDZ6RVX","short_pith_number":"pith:YAVWVMMO","schema_version":"1.0","canonical_sha256":"c02b6ab18ee22a6bc6960376f1e7d1addd475a794e61d9c91cb5978f0d7c661a","source":{"kind":"arxiv","id":"1901.05351","version":2},"attestation_state":"computed","paper":{"title":"Representation Learning on Graphs: A Reinforcement Learning Application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Laura Toni, Sephora Madjiheurem","submitted_at":"2019-01-16T15:44:13Z","abstract_excerpt":"In this work, we study value function approximation in reinforcement learning (RL) problems with high dimensional state or action spaces via a generalized version of representation policy iteration (RPI). We consider the limitations of proto-value functions (PVFs) at accurately approximating the value function in low dimensions and we highlight the importance of features learning for an improved low-dimensional value function approximation. Then, we adopt different representation learning algorithm on graphs to learn the basis functions that best represent the value function. We empirically sh"},"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":"1901.05351","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-16T15:44:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7fa81fc7d9ae356e95ebd08fbd2daecc4d044643bba39bded841594d069556b5","abstract_canon_sha256":"dfebd4f4e824c510eb64097331696536e1c05797bb23951fd60fb439f2d4411a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:09.069410Z","signature_b64":"B4qCV08nTUD5dFAaYJG1h6RYA+FRKtPgbhXCmesNh+Cm+tOYTOROHPi4xvU18HyqkpIkTc5lQO8pxZQ12EiPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c02b6ab18ee22a6bc6960376f1e7d1addd475a794e61d9c91cb5978f0d7c661a","last_reissued_at":"2026-05-17T23:56:09.068689Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:09.068689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representation Learning on Graphs: A Reinforcement Learning Application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Laura Toni, Sephora Madjiheurem","submitted_at":"2019-01-16T15:44:13Z","abstract_excerpt":"In this work, we study value function approximation in reinforcement learning (RL) problems with high dimensional state or action spaces via a generalized version of representation policy iteration (RPI). We consider the limitations of proto-value functions (PVFs) at accurately approximating the value function in low dimensions and we highlight the importance of features learning for an improved low-dimensional value function approximation. Then, we adopt different representation learning algorithm on graphs to learn the basis functions that best represent the value function. We empirically sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.05351","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":""},"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":"1901.05351","created_at":"2026-05-17T23:56:09.068811+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.05351v2","created_at":"2026-05-17T23:56:09.068811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.05351","created_at":"2026-05-17T23:56:09.068811+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAVWVMMO4IVG","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAVWVMMO4IVGXRUW","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAVWVMMO","created_at":"2026-05-18T12:33:33.725879+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/YAVWVMMO4IVGXRUWAN3PDZ6RVX","json":"https://pith.science/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX.json","graph_json":"https://pith.science/api/pith-number/YAVWVMMO4IVGXRUWAN3PDZ6RVX/graph.json","events_json":"https://pith.science/api/pith-number/YAVWVMMO4IVGXRUWAN3PDZ6RVX/events.json","paper":"https://pith.science/paper/YAVWVMMO"},"agent_actions":{"view_html":"https://pith.science/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX","download_json":"https://pith.science/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX.json","view_paper":"https://pith.science/paper/YAVWVMMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.05351&json=true","fetch_graph":"https://pith.science/api/pith-number/YAVWVMMO4IVGXRUWAN3PDZ6RVX/graph.json","fetch_events":"https://pith.science/api/pith-number/YAVWVMMO4IVGXRUWAN3PDZ6RVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX/action/storage_attestation","attest_author":"https://pith.science/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX/action/author_attestation","sign_citation":"https://pith.science/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX/action/citation_signature","submit_replication":"https://pith.science/pith/YAVWVMMO4IVGXRUWAN3PDZ6RVX/action/replication_record"}},"created_at":"2026-05-17T23:56:09.068811+00:00","updated_at":"2026-05-17T23:56:09.068811+00:00"}