{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QZBS5DFZFKYI3TZIP26IB7P3GL","short_pith_number":"pith:QZBS5DFZ","schema_version":"1.0","canonical_sha256":"86432e8cb92ab08dcf287ebc80fdfb32e19dc8183402ad7c808bf3e54850f197","source":{"kind":"arxiv","id":"2305.18420","version":2},"attestation_state":"computed","paper":{"title":"Sample Complexity of Variance-reduced Distributionally Robust Q-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jose Blanchet, Nian Si, Shengbo Wang, Zhengyuan Zhou","submitted_at":"2023-05-28T19:40:46Z","abstract_excerpt":"Dynamic decision-making under distributional shifts is of fundamental interest in theory and applications of reinforcement learning: The distribution of the environment in which the data is collected can differ from that of the environment in which the model is deployed. This paper presents two novel model-free algorithms, namely the distributionally robust Q-learning and its variance-reduced counterpart, that can effectively learn a robust policy despite distributional shifts. These algorithms are designed to efficiently approximate the $q$-function of an infinite-horizon $\\gamma$-discounted "},"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":"2305.18420","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-28T19:40:46Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"ea15274380c9b06a6272907a91af94903a369cdf268a6fae27b4bb526f0532fa","abstract_canon_sha256":"f7ceee2f4499e0cb33459b8a9fea88202171bde22a5a88f0e0bb3b8f770b6a44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:53.742727Z","signature_b64":"e+pHIm3P9MgF7sbxY+qc11QwTnyhBjL3m51LCzSkn9giyMrwO7/lbY82cnj+Q7XQPCTLW1ocFpFMSA+zT9hAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86432e8cb92ab08dcf287ebc80fdfb32e19dc8183402ad7c808bf3e54850f197","last_reissued_at":"2026-07-05T09:02:53.742188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:53.742188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample Complexity of Variance-reduced Distributionally Robust Q-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jose Blanchet, Nian Si, Shengbo Wang, Zhengyuan Zhou","submitted_at":"2023-05-28T19:40:46Z","abstract_excerpt":"Dynamic decision-making under distributional shifts is of fundamental interest in theory and applications of reinforcement learning: The distribution of the environment in which the data is collected can differ from that of the environment in which the model is deployed. This paper presents two novel model-free algorithms, namely the distributionally robust Q-learning and its variance-reduced counterpart, that can effectively learn a robust policy despite distributional shifts. These algorithms are designed to efficiently approximate the $q$-function of an infinite-horizon $\\gamma$-discounted "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18420","kind":"arxiv","version":2},"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/2305.18420/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":"2305.18420","created_at":"2026-07-05T09:02:53.742252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18420v2","created_at":"2026-07-05T09:02:53.742252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18420","created_at":"2026-07-05T09:02:53.742252+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZBS5DFZFKYI","created_at":"2026-07-05T09:02:53.742252+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZBS5DFZFKYI3TZI","created_at":"2026-07-05T09:02:53.742252+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZBS5DFZ","created_at":"2026-07-05T09:02:53.742252+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.12462","citing_title":"Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis","ref_index":85,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZBS5DFZFKYI3TZIP26IB7P3GL","json":"https://pith.science/pith/QZBS5DFZFKYI3TZIP26IB7P3GL.json","graph_json":"https://pith.science/api/pith-number/QZBS5DFZFKYI3TZIP26IB7P3GL/graph.json","events_json":"https://pith.science/api/pith-number/QZBS5DFZFKYI3TZIP26IB7P3GL/events.json","paper":"https://pith.science/paper/QZBS5DFZ"},"agent_actions":{"view_html":"https://pith.science/pith/QZBS5DFZFKYI3TZIP26IB7P3GL","download_json":"https://pith.science/pith/QZBS5DFZFKYI3TZIP26IB7P3GL.json","view_paper":"https://pith.science/paper/QZBS5DFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18420&json=true","fetch_graph":"https://pith.science/api/pith-number/QZBS5DFZFKYI3TZIP26IB7P3GL/graph.json","fetch_events":"https://pith.science/api/pith-number/QZBS5DFZFKYI3TZIP26IB7P3GL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZBS5DFZFKYI3TZIP26IB7P3GL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZBS5DFZFKYI3TZIP26IB7P3GL/action/storage_attestation","attest_author":"https://pith.science/pith/QZBS5DFZFKYI3TZIP26IB7P3GL/action/author_attestation","sign_citation":"https://pith.science/pith/QZBS5DFZFKYI3TZIP26IB7P3GL/action/citation_signature","submit_replication":"https://pith.science/pith/QZBS5DFZFKYI3TZIP26IB7P3GL/action/replication_record"}},"created_at":"2026-07-05T09:02:53.742252+00:00","updated_at":"2026-07-05T09:02:53.742252+00:00"}