{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CQNYUTN6KV4W2E2ZBM2R3JITQR","short_pith_number":"pith:CQNYUTN6","schema_version":"1.0","canonical_sha256":"141b8a4dbe55796d13590b351da513845b02cd4e9c101cbc6743b08babc9d493","source":{"kind":"arxiv","id":"2608.07772","version":1},"attestation_state":"computed","paper":{"title":"The Sample Complexity of Policy Learning with Mu-Resets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gene Li","submitted_at":"2026-08-07T21:42:37Z","abstract_excerpt":"We study policy-based reinforcement learning under the $\\mu$-resets interaction protocol of Kakade and Langford [KL02]. This interaction protocol enables the learner to sample trajectories from a given exploratory reset distribution $\\mu$, in addition to the starting distribution. We resolve the question raised by [KLS25] on the role of policy realizability for the sample complexity of this problem. Critically, the dependence on horizon $H$ is governed by the notion of coverage assumed of the reset distribution. Under bounded all-policy concentrability, we show a $\\exp(\\Omega(H))$ sample compl"},"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":"2608.07772","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T21:42:37Z","cross_cats_sorted":[],"title_canon_sha256":"7fa5d11f64008160ed32f2a054ee51d665a9b83c6e5b56831e2935fc7fd6386f","abstract_canon_sha256":"b80a6419f10e4ffd788548a4f7ec33624c5855887abb82d6deaea7a34e847bea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T00:15:55.740741Z","signature_b64":"3prCd3aBazVmy3lpSRYdsMq+Fbo4qE16Cn1u+KUa9Fkf9GU/3DPWiqYx0A8XzUTSJCpgEcUB2yKPjGOZS3zKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"141b8a4dbe55796d13590b351da513845b02cd4e9c101cbc6743b08babc9d493","last_reissued_at":"2026-08-11T00:15:55.738505Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T00:15:55.738505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Sample Complexity of Policy Learning with Mu-Resets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gene Li","submitted_at":"2026-08-07T21:42:37Z","abstract_excerpt":"We study policy-based reinforcement learning under the $\\mu$-resets interaction protocol of Kakade and Langford [KL02]. This interaction protocol enables the learner to sample trajectories from a given exploratory reset distribution $\\mu$, in addition to the starting distribution. We resolve the question raised by [KLS25] on the role of policy realizability for the sample complexity of this problem. Critically, the dependence on horizon $H$ is governed by the notion of coverage assumed of the reset distribution. Under bounded all-policy concentrability, we show a $\\exp(\\Omega(H))$ sample compl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07772","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/2608.07772/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":"2608.07772","created_at":"2026-08-11T00:15:55.738870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07772v1","created_at":"2026-08-11T00:15:55.738870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07772","created_at":"2026-08-11T00:15:55.738870+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQNYUTN6KV4W","created_at":"2026-08-11T00:15:55.738870+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQNYUTN6KV4W2E2Z","created_at":"2026-08-11T00:15:55.738870+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQNYUTN6","created_at":"2026-08-11T00:15:55.738870+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/CQNYUTN6KV4W2E2ZBM2R3JITQR","json":"https://pith.science/pith/CQNYUTN6KV4W2E2ZBM2R3JITQR.json","graph_json":"https://pith.science/api/pith-number/CQNYUTN6KV4W2E2ZBM2R3JITQR/graph.json","events_json":"https://pith.science/api/pith-number/CQNYUTN6KV4W2E2ZBM2R3JITQR/events.json","paper":"https://pith.science/paper/CQNYUTN6"},"agent_actions":{"view_html":"https://pith.science/pith/CQNYUTN6KV4W2E2ZBM2R3JITQR","download_json":"https://pith.science/pith/CQNYUTN6KV4W2E2ZBM2R3JITQR.json","view_paper":"https://pith.science/paper/CQNYUTN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07772&json=true","fetch_graph":"https://pith.science/api/pith-number/CQNYUTN6KV4W2E2ZBM2R3JITQR/graph.json","fetch_events":"https://pith.science/api/pith-number/CQNYUTN6KV4W2E2ZBM2R3JITQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQNYUTN6KV4W2E2ZBM2R3JITQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQNYUTN6KV4W2E2ZBM2R3JITQR/action/storage_attestation","attest_author":"https://pith.science/pith/CQNYUTN6KV4W2E2ZBM2R3JITQR/action/author_attestation","sign_citation":"https://pith.science/pith/CQNYUTN6KV4W2E2ZBM2R3JITQR/action/citation_signature","submit_replication":"https://pith.science/pith/CQNYUTN6KV4W2E2ZBM2R3JITQR/action/replication_record"}},"created_at":"2026-08-11T00:15:55.738870+00:00","updated_at":"2026-08-11T00:15:55.738870+00:00"}