{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DMSAIUCGRADORSIBOE3BFWKST7","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":"8114e577139627ae78147380792b63790ace9342523370ddf3fd218c00682dee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T14:59:15Z","title_canon_sha256":"0a57fbc24e2cb665ee4ee0a33bf5ac85b21f3f8e2d6e47c5ddb1f599d690d616"},"schema_version":"1.0","source":{"id":"2505.12037","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12037","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12037v1","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12037","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"DMSAIUCGRADO","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"DMSAIUCGRADORSIB","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"DMSAIUCG","created_at":"2026-07-05T11:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:8f189dff8191328982897049cb46cad3ed6fab9b14df350390ad483c068b1942","target":"graph","created_at":"2026-07-05T11:04:57Z","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/2505.12037/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jiashuo Jiang, Yiming Zong, Yinyu Ye","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T14:59:15Z","title":"Adaptive Resolving Methods for Reinforcement Learning with Function Approximations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12037","kind":"arxiv","version":1},"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":"sha256:62e27d95d9dc65f834ea794e73cf5bd8fc3c572fd8c25e4cf82e201566909120","target":"record","created_at":"2026-07-05T11:04:57Z","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":"8114e577139627ae78147380792b63790ace9342523370ddf3fd218c00682dee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T14:59:15Z","title_canon_sha256":"0a57fbc24e2cb665ee4ee0a33bf5ac85b21f3f8e2d6e47c5ddb1f599d690d616"},"schema_version":"1.0","source":{"id":"2505.12037","kind":"arxiv","version":1}},"canonical_sha256":"1b240450468806e8c901713612d9529ff99949fda76c93875cf1f172bb0f4985","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b240450468806e8c901713612d9529ff99949fda76c93875cf1f172bb0f4985","first_computed_at":"2026-07-05T11:04:57.322806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:57.322806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4S0Mq/p6PM0SQoGkn1Zn01d3QW86wdQAnl8iWAmv5ETYMG7VKMcKxck/SXnCHQNMp7Lik73mOTlfrJc3oESCAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:57.323302Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12037","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62e27d95d9dc65f834ea794e73cf5bd8fc3c572fd8c25e4cf82e201566909120","sha256:8f189dff8191328982897049cb46cad3ed6fab9b14df350390ad483c068b1942"],"state_sha256":"04b4b2b3a56d9f6b246dbf7f41a4eb1e9707a94abff43cb3411784bd517d6f20"}