{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RQICY4NVXGVLOVTZGUZWR4M3OO","short_pith_number":"pith:RQICY4NV","schema_version":"1.0","canonical_sha256":"8c102c71b5b9aab75679353368f19b73a275797bd87458990a281020a8ff1f89","source":{"kind":"arxiv","id":"2501.04879","version":1},"attestation_state":"computed","paper":{"title":"Multilinear Tensor Low-Rank Approximation for Policy-Gradient Methods in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonio G. Marques, Hoi-To Wai, Sergio Rozada","submitted_at":"2025-01-08T23:22:08Z","abstract_excerpt":"Reinforcement learning (RL) aims to estimate the action to take given a (time-varying) state, with the goal of maximizing a cumulative reward function. Predominantly, there are two families of algorithms to solve RL problems: value-based and policy-based methods, with the latter designed to learn a probabilistic parametric policy from states to actions. Most contemporary approaches implement this policy using a neural network (NN). However, NNs usually face issues related to convergence, architectural suitability, hyper-parameter selection, and underutilization of the redundancies of the state"},"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":"2501.04879","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T23:22:08Z","cross_cats_sorted":[],"title_canon_sha256":"8496c541685ced74d66ac5d2c36f11ed7d1a5f972f55402c603d714fe865de26","abstract_canon_sha256":"dc5e82b53156ae9a049e76202ac1a6f585cdbef29a0b17d73f85fbff7419e52b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:47.905818Z","signature_b64":"i5YEWxlN49gPH3sfEig/okmcvnmym3eCLvXbYiMdquFHUO0Wt22eBsgXfXmUKZgEogfU+kql+7hgwDp6KrdTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c102c71b5b9aab75679353368f19b73a275797bd87458990a281020a8ff1f89","last_reissued_at":"2026-07-05T09:58:47.905399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:47.905399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilinear Tensor Low-Rank Approximation for Policy-Gradient Methods in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonio G. Marques, Hoi-To Wai, Sergio Rozada","submitted_at":"2025-01-08T23:22:08Z","abstract_excerpt":"Reinforcement learning (RL) aims to estimate the action to take given a (time-varying) state, with the goal of maximizing a cumulative reward function. Predominantly, there are two families of algorithms to solve RL problems: value-based and policy-based methods, with the latter designed to learn a probabilistic parametric policy from states to actions. Most contemporary approaches implement this policy using a neural network (NN). However, NNs usually face issues related to convergence, architectural suitability, hyper-parameter selection, and underutilization of the redundancies of the state"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04879","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/2501.04879/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":"2501.04879","created_at":"2026-07-05T09:58:47.905456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04879v1","created_at":"2026-07-05T09:58:47.905456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04879","created_at":"2026-07-05T09:58:47.905456+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQICY4NVXGVL","created_at":"2026-07-05T09:58:47.905456+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQICY4NVXGVLOVTZ","created_at":"2026-07-05T09:58:47.905456+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQICY4NV","created_at":"2026-07-05T09:58:47.905456+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/RQICY4NVXGVLOVTZGUZWR4M3OO","json":"https://pith.science/pith/RQICY4NVXGVLOVTZGUZWR4M3OO.json","graph_json":"https://pith.science/api/pith-number/RQICY4NVXGVLOVTZGUZWR4M3OO/graph.json","events_json":"https://pith.science/api/pith-number/RQICY4NVXGVLOVTZGUZWR4M3OO/events.json","paper":"https://pith.science/paper/RQICY4NV"},"agent_actions":{"view_html":"https://pith.science/pith/RQICY4NVXGVLOVTZGUZWR4M3OO","download_json":"https://pith.science/pith/RQICY4NVXGVLOVTZGUZWR4M3OO.json","view_paper":"https://pith.science/paper/RQICY4NV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04879&json=true","fetch_graph":"https://pith.science/api/pith-number/RQICY4NVXGVLOVTZGUZWR4M3OO/graph.json","fetch_events":"https://pith.science/api/pith-number/RQICY4NVXGVLOVTZGUZWR4M3OO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQICY4NVXGVLOVTZGUZWR4M3OO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQICY4NVXGVLOVTZGUZWR4M3OO/action/storage_attestation","attest_author":"https://pith.science/pith/RQICY4NVXGVLOVTZGUZWR4M3OO/action/author_attestation","sign_citation":"https://pith.science/pith/RQICY4NVXGVLOVTZGUZWR4M3OO/action/citation_signature","submit_replication":"https://pith.science/pith/RQICY4NVXGVLOVTZGUZWR4M3OO/action/replication_record"}},"created_at":"2026-07-05T09:58:47.905456+00:00","updated_at":"2026-07-05T09:58:47.905456+00:00"}