{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OBA4SKDRW2B2DVNRYRVS5MXZIT","short_pith_number":"pith:OBA4SKDR","schema_version":"1.0","canonical_sha256":"7041c92871b683a1d5b1c46b2eb2f944ece799c852e76f3b9b790df9ac2c5022","source":{"kind":"arxiv","id":"2507.12383","version":1},"attestation_state":"computed","paper":{"title":"Improving Reinforcement Learning Sample-Efficiency using Local Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arvind Easwaran, Mohit Prashant","submitted_at":"2025-07-16T16:31:17Z","abstract_excerpt":"In this study, we derive Probably Approximately Correct (PAC) bounds on the asymptotic sample-complexity for RL within the infinite-horizon Markov Decision Process (MDP) setting that are sharper than those in existing literature. The premise of our study is twofold: firstly, the further two states are from each other, transition-wise, the less relevant the value of the first state is when learning the $\\epsilon$-optimal value of the second; secondly, the amount of 'effort', sample-complexity-wise, expended in learning the $\\epsilon$-optimal value of a state is independent of the number of samp"},"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":"2507.12383","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T16:31:17Z","cross_cats_sorted":[],"title_canon_sha256":"800078567b61d73accc0fd4ce68882b5afaa2852aa0c2400b2b879618e706a29","abstract_canon_sha256":"33937186ee26b2fb776f2d51823c82b8501fdd01f82cb290ccd8ff3abe1f4f0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:19.395300Z","signature_b64":"jtMi8H19RcWBN2Cy9khPkJnqQGKiVWL9TWkPspSA6iIeUD3rF1dMaKylXh+bOAg0ZJf7UNxT8BXBoIk+PwFQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7041c92871b683a1d5b1c46b2eb2f944ece799c852e76f3b9b790df9ac2c5022","last_reissued_at":"2026-07-05T11:38:19.394821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:19.394821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Reinforcement Learning Sample-Efficiency using Local Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arvind Easwaran, Mohit Prashant","submitted_at":"2025-07-16T16:31:17Z","abstract_excerpt":"In this study, we derive Probably Approximately Correct (PAC) bounds on the asymptotic sample-complexity for RL within the infinite-horizon Markov Decision Process (MDP) setting that are sharper than those in existing literature. The premise of our study is twofold: firstly, the further two states are from each other, transition-wise, the less relevant the value of the first state is when learning the $\\epsilon$-optimal value of the second; secondly, the amount of 'effort', sample-complexity-wise, expended in learning the $\\epsilon$-optimal value of a state is independent of the number of samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12383","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/2507.12383/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":"2507.12383","created_at":"2026-07-05T11:38:19.394887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12383v1","created_at":"2026-07-05T11:38:19.394887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12383","created_at":"2026-07-05T11:38:19.394887+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBA4SKDRW2B2","created_at":"2026-07-05T11:38:19.394887+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBA4SKDRW2B2DVNR","created_at":"2026-07-05T11:38:19.394887+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBA4SKDR","created_at":"2026-07-05T11:38:19.394887+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/OBA4SKDRW2B2DVNRYRVS5MXZIT","json":"https://pith.science/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT.json","graph_json":"https://pith.science/api/pith-number/OBA4SKDRW2B2DVNRYRVS5MXZIT/graph.json","events_json":"https://pith.science/api/pith-number/OBA4SKDRW2B2DVNRYRVS5MXZIT/events.json","paper":"https://pith.science/paper/OBA4SKDR"},"agent_actions":{"view_html":"https://pith.science/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT","download_json":"https://pith.science/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT.json","view_paper":"https://pith.science/paper/OBA4SKDR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12383&json=true","fetch_graph":"https://pith.science/api/pith-number/OBA4SKDRW2B2DVNRYRVS5MXZIT/graph.json","fetch_events":"https://pith.science/api/pith-number/OBA4SKDRW2B2DVNRYRVS5MXZIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT/action/storage_attestation","attest_author":"https://pith.science/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT/action/author_attestation","sign_citation":"https://pith.science/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT/action/citation_signature","submit_replication":"https://pith.science/pith/OBA4SKDRW2B2DVNRYRVS5MXZIT/action/replication_record"}},"created_at":"2026-07-05T11:38:19.394887+00:00","updated_at":"2026-07-05T11:38:19.394887+00:00"}