{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MLDKJS2B5UX7W42PDQSZJMJEFE","short_pith_number":"pith:MLDKJS2B","schema_version":"1.0","canonical_sha256":"62c6a4cb41ed2ffb734f1c2594b12429246cfd4ea131a29e50a3ac4f00fb2e41","source":{"kind":"arxiv","id":"1811.07201","version":1},"attestation_state":"computed","paper":{"title":"Recursive Sparse Pseudo-input Gaussian Process SARSA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Brendan Englot, John Martin","submitted_at":"2018-11-17T18:06:37Z","abstract_excerpt":"The class of Gaussian Process (GP) methods for Temporal Difference learning has shown promise for data-efficient model-free Reinforcement Learning. In this paper, we consider a recent variant of the GP-SARSA algorithm, called Sparse Pseudo-input Gaussian Process SARSA (SPGP-SARSA), and derive recursive formulas for its predictive moments. This extension promotes greater memory efficiency, since previous computations can be reused and, interestingly, it provides a technique for updating value estimates on a multiple timescales"},"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":"1811.07201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-17T18:06:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7802e77b196804fc6f65b047cc459821e452bf24836f506ef2874700a4feab6a","abstract_canon_sha256":"621b0d98a0209dfcb2e68b246ef82d3771c79080e6e994af4844db81f20afa76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:28.642856Z","signature_b64":"ZbwUo5JrbIMVqwnmaQuoNth+l5EiR01WMUoVWtYPjpRWlGRsQE8qemn4xebdsvZ/B6wQ3QzJg+2Ls2WCH04WCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62c6a4cb41ed2ffb734f1c2594b12429246cfd4ea131a29e50a3ac4f00fb2e41","last_reissued_at":"2026-05-18T00:00:28.642365Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:28.642365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recursive Sparse Pseudo-input Gaussian Process SARSA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Brendan Englot, John Martin","submitted_at":"2018-11-17T18:06:37Z","abstract_excerpt":"The class of Gaussian Process (GP) methods for Temporal Difference learning has shown promise for data-efficient model-free Reinforcement Learning. In this paper, we consider a recent variant of the GP-SARSA algorithm, called Sparse Pseudo-input Gaussian Process SARSA (SPGP-SARSA), and derive recursive formulas for its predictive moments. This extension promotes greater memory efficiency, since previous computations can be reused and, interestingly, it provides a technique for updating value estimates on a multiple timescales"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07201","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":""},"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":"1811.07201","created_at":"2026-05-18T00:00:28.642440+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.07201v1","created_at":"2026-05-18T00:00:28.642440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07201","created_at":"2026-05-18T00:00:28.642440+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLDKJS2B5UX7","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLDKJS2B5UX7W42P","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLDKJS2B","created_at":"2026-05-18T12:32:37.024351+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/MLDKJS2B5UX7W42PDQSZJMJEFE","json":"https://pith.science/pith/MLDKJS2B5UX7W42PDQSZJMJEFE.json","graph_json":"https://pith.science/api/pith-number/MLDKJS2B5UX7W42PDQSZJMJEFE/graph.json","events_json":"https://pith.science/api/pith-number/MLDKJS2B5UX7W42PDQSZJMJEFE/events.json","paper":"https://pith.science/paper/MLDKJS2B"},"agent_actions":{"view_html":"https://pith.science/pith/MLDKJS2B5UX7W42PDQSZJMJEFE","download_json":"https://pith.science/pith/MLDKJS2B5UX7W42PDQSZJMJEFE.json","view_paper":"https://pith.science/paper/MLDKJS2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.07201&json=true","fetch_graph":"https://pith.science/api/pith-number/MLDKJS2B5UX7W42PDQSZJMJEFE/graph.json","fetch_events":"https://pith.science/api/pith-number/MLDKJS2B5UX7W42PDQSZJMJEFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLDKJS2B5UX7W42PDQSZJMJEFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLDKJS2B5UX7W42PDQSZJMJEFE/action/storage_attestation","attest_author":"https://pith.science/pith/MLDKJS2B5UX7W42PDQSZJMJEFE/action/author_attestation","sign_citation":"https://pith.science/pith/MLDKJS2B5UX7W42PDQSZJMJEFE/action/citation_signature","submit_replication":"https://pith.science/pith/MLDKJS2B5UX7W42PDQSZJMJEFE/action/replication_record"}},"created_at":"2026-05-18T00:00:28.642440+00:00","updated_at":"2026-05-18T00:00:28.642440+00:00"}