{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QC5PLRAHSXC6JAHFI62YGE62BD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6c1ea4d97a9c6f4f8a58007d99ec974afe70fb5f4f51e0c43f274f3b81875fa1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-21T00:13:54Z","title_canon_sha256":"1cf999675a48d280d925318ecd44ba28101c03508d2fd5b8ece1285f01848b5e"},"schema_version":"1.0","source":{"id":"2201.09736","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.09736","created_at":"2026-07-05T08:23:51Z"},{"alias_kind":"arxiv_version","alias_value":"2201.09736v3","created_at":"2026-07-05T08:23:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.09736","created_at":"2026-07-05T08:23:51Z"},{"alias_kind":"pith_short_12","alias_value":"QC5PLRAHSXC6","created_at":"2026-07-05T08:23:51Z"},{"alias_kind":"pith_short_16","alias_value":"QC5PLRAHSXC6JAHF","created_at":"2026-07-05T08:23:51Z"},{"alias_kind":"pith_short_8","alias_value":"QC5PLRAH","created_at":"2026-07-05T08:23:51Z"}],"graph_snapshots":[{"event_id":"sha256:ec67b6d055c3f5cbff776fad6c13a495dac9c337d43ef4491602fbcaf317657f","target":"graph","created_at":"2026-07-05T08:23:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2201.09736/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Value-function (VF) approximation is a central problem in Reinforcement Learning (RL). Classical non-parametric VF estimation suffers from the curse of dimensionality. As a result, parsimonious parametric models have been adopted to approximate VFs in high-dimensional spaces, with most efforts being focused on linear and neural-network-based approaches. Differently, this paper puts forth a a parsimonious non-parametric approach, where we use stochastic low-rank algorithms to estimate the VF matrix in an online and model-free fashion. Furthermore, as VFs tend to be multi-dimensional, we propose","authors_text":"Antonio G. Marques, Santiago Paternain, Sergio Rozada","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-21T00:13:54Z","title":"Tensor and Matrix Low-Rank Value-Function Approximation in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.09736","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5bf5cd43200fab2c10d933f2283f2da85693955948f9d388654eb5744ee47ac3","target":"record","created_at":"2026-07-05T08:23:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6c1ea4d97a9c6f4f8a58007d99ec974afe70fb5f4f51e0c43f274f3b81875fa1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-21T00:13:54Z","title_canon_sha256":"1cf999675a48d280d925318ecd44ba28101c03508d2fd5b8ece1285f01848b5e"},"schema_version":"1.0","source":{"id":"2201.09736","kind":"arxiv","version":3}},"canonical_sha256":"80baf5c40795c5e480e547b58313da08cfb03500ea73f2cb3030fcb6556ecede","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80baf5c40795c5e480e547b58313da08cfb03500ea73f2cb3030fcb6556ecede","first_computed_at":"2026-07-05T08:23:51.205924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:51.205924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CXrzTVVAwqgHpDiDhEL5MYucdkbDTBH0p+hE2EaEeRSEQNU1NODpV9pUtWc3G7LtLC33lKMpn/3jSJO7bgWuBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:51.206282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.09736","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bf5cd43200fab2c10d933f2283f2da85693955948f9d388654eb5744ee47ac3","sha256:ec67b6d055c3f5cbff776fad6c13a495dac9c337d43ef4491602fbcaf317657f"],"state_sha256":"855ef1629626de77d59eff49cad35e3c748db3ce85119f976e3c361e97b36057"}