{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RCBDWTQFZW3NCO2YUVYETYYOET","short_pith_number":"pith:RCBDWTQF","schema_version":"1.0","canonical_sha256":"88823b4e05cdb6d13b58a57049e30e24dee4d82c2b5d92900a65211b53def2e6","source":{"kind":"arxiv","id":"2305.17552","version":2},"attestation_state":"computed","paper":{"title":"Online Nonstochastic Model-Free Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Arushi Gupta, Elad Hazan, Karan Singh, Udaya Ghai, Wenhan Xia","submitted_at":"2023-05-27T19:02:55Z","abstract_excerpt":"We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of unmodeled disturbances in such settings. Moreover, optimizing linear state-based policies pose an obstacle for efficient optimization, leading to nonconvex objectives, even in benign environments like linear dynamical systems.\n  Drawing inspiration from recent advancements in model-based control, we introduce a novel class of policies centered on disturbance "},"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":"2305.17552","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-27T19:02:55Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"40f23d0a38afc4e427334b2a0e9fb2a7dbaea9a35bc9535bf02a61c160dab0e7","abstract_canon_sha256":"ebf4d99f933b7f0668ef93ce2ed12bdbeae6aa9bcb92f5057fffb6f51035985f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:37.983432Z","signature_b64":"XlwsOIBVz6ntrFjDkiZ+EtXx7Zh0A0SjZU5DOujbZboI/uL9gc0Q0J5B8ByvEPFAS1XY5i9s9EoDrhHQKdUICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88823b4e05cdb6d13b58a57049e30e24dee4d82c2b5d92900a65211b53def2e6","last_reissued_at":"2026-07-05T07:07:37.982918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:37.982918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Nonstochastic Model-Free Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Arushi Gupta, Elad Hazan, Karan Singh, Udaya Ghai, Wenhan Xia","submitted_at":"2023-05-27T19:02:55Z","abstract_excerpt":"We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of unmodeled disturbances in such settings. Moreover, optimizing linear state-based policies pose an obstacle for efficient optimization, leading to nonconvex objectives, even in benign environments like linear dynamical systems.\n  Drawing inspiration from recent advancements in model-based control, we introduce a novel class of policies centered on disturbance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17552","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/2305.17552/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":"2305.17552","created_at":"2026-07-05T07:07:37.982981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17552v2","created_at":"2026-07-05T07:07:37.982981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17552","created_at":"2026-07-05T07:07:37.982981+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCBDWTQFZW3N","created_at":"2026-07-05T07:07:37.982981+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCBDWTQFZW3NCO2Y","created_at":"2026-07-05T07:07:37.982981+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCBDWTQF","created_at":"2026-07-05T07:07:37.982981+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/RCBDWTQFZW3NCO2YUVYETYYOET","json":"https://pith.science/pith/RCBDWTQFZW3NCO2YUVYETYYOET.json","graph_json":"https://pith.science/api/pith-number/RCBDWTQFZW3NCO2YUVYETYYOET/graph.json","events_json":"https://pith.science/api/pith-number/RCBDWTQFZW3NCO2YUVYETYYOET/events.json","paper":"https://pith.science/paper/RCBDWTQF"},"agent_actions":{"view_html":"https://pith.science/pith/RCBDWTQFZW3NCO2YUVYETYYOET","download_json":"https://pith.science/pith/RCBDWTQFZW3NCO2YUVYETYYOET.json","view_paper":"https://pith.science/paper/RCBDWTQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17552&json=true","fetch_graph":"https://pith.science/api/pith-number/RCBDWTQFZW3NCO2YUVYETYYOET/graph.json","fetch_events":"https://pith.science/api/pith-number/RCBDWTQFZW3NCO2YUVYETYYOET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCBDWTQFZW3NCO2YUVYETYYOET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCBDWTQFZW3NCO2YUVYETYYOET/action/storage_attestation","attest_author":"https://pith.science/pith/RCBDWTQFZW3NCO2YUVYETYYOET/action/author_attestation","sign_citation":"https://pith.science/pith/RCBDWTQFZW3NCO2YUVYETYYOET/action/citation_signature","submit_replication":"https://pith.science/pith/RCBDWTQFZW3NCO2YUVYETYYOET/action/replication_record"}},"created_at":"2026-07-05T07:07:37.982981+00:00","updated_at":"2026-07-05T07:07:37.982981+00:00"}