{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:3VV65MVT2SVGZCOMMPP7OUY5BP","short_pith_number":"pith:3VV65MVT","schema_version":"1.0","canonical_sha256":"dd6beeb2b3d4aa6c89cc63dff7531d0bce1fbcf4b6f3d24c617efca0a35a1606","source":{"kind":"arxiv","id":"1112.4722","version":2},"attestation_state":"computed","paper":{"title":"Modeling transition dynamics in MDPs with RKHS embeddings of conditional distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arthur Gretton, Guy Lever, Luca Baldassarre, Massimiliano Pontil, Steffen Gr\\\"unew\\\"alder","submitted_at":"2011-12-20T15:21:26Z","abstract_excerpt":"We propose a new, nonparametric approach to estimating the value function in reinforcement learning. This approach makes use of a recently developed representation of conditional distributions as functions in a reproducing kernel Hilbert space. Such representations bypass the need for estimating transition probabilities, and apply to any domain on which kernels can be defined. Our approach avoids the need to approximate intractable integrals since expectations are represented as RKHS inner products whose computation has linear complexity in the sample size. Thus, we can efficiently perform val"},"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":"1112.4722","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-12-20T15:21:26Z","cross_cats_sorted":[],"title_canon_sha256":"9c772cea851c70dee7ac2decbfbd7918212eb6ad3ec001fb818ecc99a88686c3","abstract_canon_sha256":"611f2c93772546f0c83ead8367f188c94b9435bcb614cb59b25b9d41855a1376"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:42:54.073503Z","signature_b64":"ITqcJnDVZr/RebiKCfeXazIvgM9XGGdIZrNrgxH2XZ3Xpg7Fwz7YE66pwA6kKIXdgryEl/A197GAqTsKqXKgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd6beeb2b3d4aa6c89cc63dff7531d0bce1fbcf4b6f3d24c617efca0a35a1606","last_reissued_at":"2026-05-18T03:42:54.073041Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:42:54.073041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling transition dynamics in MDPs with RKHS embeddings of conditional distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arthur Gretton, Guy Lever, Luca Baldassarre, Massimiliano Pontil, Steffen Gr\\\"unew\\\"alder","submitted_at":"2011-12-20T15:21:26Z","abstract_excerpt":"We propose a new, nonparametric approach to estimating the value function in reinforcement learning. This approach makes use of a recently developed representation of conditional distributions as functions in a reproducing kernel Hilbert space. Such representations bypass the need for estimating transition probabilities, and apply to any domain on which kernels can be defined. Our approach avoids the need to approximate intractable integrals since expectations are represented as RKHS inner products whose computation has linear complexity in the sample size. Thus, we can efficiently perform val"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1112.4722","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":"1112.4722","created_at":"2026-05-18T03:42:54.073110+00:00"},{"alias_kind":"arxiv_version","alias_value":"1112.4722v2","created_at":"2026-05-18T03:42:54.073110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1112.4722","created_at":"2026-05-18T03:42:54.073110+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VV65MVT2SVG","created_at":"2026-05-18T12:26:20.644004+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VV65MVT2SVGZCOM","created_at":"2026-05-18T12:26:20.644004+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VV65MVT","created_at":"2026-05-18T12:26:20.644004+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/3VV65MVT2SVGZCOMMPP7OUY5BP","json":"https://pith.science/pith/3VV65MVT2SVGZCOMMPP7OUY5BP.json","graph_json":"https://pith.science/api/pith-number/3VV65MVT2SVGZCOMMPP7OUY5BP/graph.json","events_json":"https://pith.science/api/pith-number/3VV65MVT2SVGZCOMMPP7OUY5BP/events.json","paper":"https://pith.science/paper/3VV65MVT"},"agent_actions":{"view_html":"https://pith.science/pith/3VV65MVT2SVGZCOMMPP7OUY5BP","download_json":"https://pith.science/pith/3VV65MVT2SVGZCOMMPP7OUY5BP.json","view_paper":"https://pith.science/paper/3VV65MVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1112.4722&json=true","fetch_graph":"https://pith.science/api/pith-number/3VV65MVT2SVGZCOMMPP7OUY5BP/graph.json","fetch_events":"https://pith.science/api/pith-number/3VV65MVT2SVGZCOMMPP7OUY5BP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VV65MVT2SVGZCOMMPP7OUY5BP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VV65MVT2SVGZCOMMPP7OUY5BP/action/storage_attestation","attest_author":"https://pith.science/pith/3VV65MVT2SVGZCOMMPP7OUY5BP/action/author_attestation","sign_citation":"https://pith.science/pith/3VV65MVT2SVGZCOMMPP7OUY5BP/action/citation_signature","submit_replication":"https://pith.science/pith/3VV65MVT2SVGZCOMMPP7OUY5BP/action/replication_record"}},"created_at":"2026-05-18T03:42:54.073110+00:00","updated_at":"2026-05-18T03:42:54.073110+00:00"}