{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DMSAIUCGRADORSIBOE3BFWKST7","short_pith_number":"pith:DMSAIUCG","schema_version":"1.0","canonical_sha256":"1b240450468806e8c901713612d9529ff99949fda76c93875cf1f172bb0f4985","source":{"kind":"arxiv","id":"2505.12037","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Resolving Methods for Reinforcement Learning with Function Approximations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiashuo Jiang, Yiming Zong, Yinyu Ye","submitted_at":"2025-05-17T14:59:15Z","abstract_excerpt":"Reinforcement learning (RL) problems are fundamental in online decision-making and have been instrumental in finding an optimal policy for Markov decision processes (MDPs). Function approximations are usually deployed to handle large or infinite state-action space. In our work, we consider the RL problems with function approximation and we develop a new algorithm to solve it efficiently. Our algorithm is based on the linear programming (LP) reformulation and it resolves the LP at each iteration improved with new data arrival. Such a resolving scheme enables our algorithm to achieve an instance"},"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":"2505.12037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T14:59:15Z","cross_cats_sorted":[],"title_canon_sha256":"0a57fbc24e2cb665ee4ee0a33bf5ac85b21f3f8e2d6e47c5ddb1f599d690d616","abstract_canon_sha256":"8114e577139627ae78147380792b63790ace9342523370ddf3fd218c00682dee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:57.323302Z","signature_b64":"4S0Mq/p6PM0SQoGkn1Zn01d3QW86wdQAnl8iWAmv5ETYMG7VKMcKxck/SXnCHQNMp7Lik73mOTlfrJc3oESCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b240450468806e8c901713612d9529ff99949fda76c93875cf1f172bb0f4985","last_reissued_at":"2026-07-05T11:04:57.322806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:57.322806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Resolving Methods for Reinforcement Learning with Function Approximations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiashuo Jiang, Yiming Zong, Yinyu Ye","submitted_at":"2025-05-17T14:59:15Z","abstract_excerpt":"Reinforcement learning (RL) problems are fundamental in online decision-making and have been instrumental in finding an optimal policy for Markov decision processes (MDPs). Function approximations are usually deployed to handle large or infinite state-action space. In our work, we consider the RL problems with function approximation and we develop a new algorithm to solve it efficiently. Our algorithm is based on the linear programming (LP) reformulation and it resolves the LP at each iteration improved with new data arrival. Such a resolving scheme enables our algorithm to achieve an instance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12037","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/2505.12037/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":"2505.12037","created_at":"2026-07-05T11:04:57.322875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12037v1","created_at":"2026-07-05T11:04:57.322875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12037","created_at":"2026-07-05T11:04:57.322875+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMSAIUCGRADO","created_at":"2026-07-05T11:04:57.322875+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMSAIUCGRADORSIB","created_at":"2026-07-05T11:04:57.322875+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMSAIUCG","created_at":"2026-07-05T11:04:57.322875+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/DMSAIUCGRADORSIBOE3BFWKST7","json":"https://pith.science/pith/DMSAIUCGRADORSIBOE3BFWKST7.json","graph_json":"https://pith.science/api/pith-number/DMSAIUCGRADORSIBOE3BFWKST7/graph.json","events_json":"https://pith.science/api/pith-number/DMSAIUCGRADORSIBOE3BFWKST7/events.json","paper":"https://pith.science/paper/DMSAIUCG"},"agent_actions":{"view_html":"https://pith.science/pith/DMSAIUCGRADORSIBOE3BFWKST7","download_json":"https://pith.science/pith/DMSAIUCGRADORSIBOE3BFWKST7.json","view_paper":"https://pith.science/paper/DMSAIUCG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12037&json=true","fetch_graph":"https://pith.science/api/pith-number/DMSAIUCGRADORSIBOE3BFWKST7/graph.json","fetch_events":"https://pith.science/api/pith-number/DMSAIUCGRADORSIBOE3BFWKST7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMSAIUCGRADORSIBOE3BFWKST7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMSAIUCGRADORSIBOE3BFWKST7/action/storage_attestation","attest_author":"https://pith.science/pith/DMSAIUCGRADORSIBOE3BFWKST7/action/author_attestation","sign_citation":"https://pith.science/pith/DMSAIUCGRADORSIBOE3BFWKST7/action/citation_signature","submit_replication":"https://pith.science/pith/DMSAIUCGRADORSIBOE3BFWKST7/action/replication_record"}},"created_at":"2026-07-05T11:04:57.322875+00:00","updated_at":"2026-07-05T11:04:57.322875+00:00"}