{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RCBDWTQFZW3NCO2YUVYETYYOET","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":"ebf4d99f933b7f0668ef93ce2ed12bdbeae6aa9bcb92f5057fffb6f51035985f","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-27T19:02:55Z","title_canon_sha256":"40f23d0a38afc4e427334b2a0e9fb2a7dbaea9a35bc9535bf02a61c160dab0e7"},"schema_version":"1.0","source":{"id":"2305.17552","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17552","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17552v2","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17552","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"pith_short_12","alias_value":"RCBDWTQFZW3N","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"pith_short_16","alias_value":"RCBDWTQFZW3NCO2Y","created_at":"2026-07-05T07:07:37Z"},{"alias_kind":"pith_short_8","alias_value":"RCBDWTQF","created_at":"2026-07-05T07:07:37Z"}],"graph_snapshots":[{"event_id":"sha256:4d96d43395e6b5010af367c5c3c121e6ede506136e41092a5d31e38bbcb191c2","target":"graph","created_at":"2026-07-05T07:07:37Z","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/2305.17552/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Arushi Gupta, Elad Hazan, Karan Singh, Udaya Ghai, Wenhan Xia","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-27T19:02:55Z","title":"Online Nonstochastic Model-Free Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17552","kind":"arxiv","version":2},"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:e8b1ac564128b48108d43854bff28fdae6218f67e3613ae7dce9fa36573ed04a","target":"record","created_at":"2026-07-05T07:07:37Z","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":"ebf4d99f933b7f0668ef93ce2ed12bdbeae6aa9bcb92f5057fffb6f51035985f","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-27T19:02:55Z","title_canon_sha256":"40f23d0a38afc4e427334b2a0e9fb2a7dbaea9a35bc9535bf02a61c160dab0e7"},"schema_version":"1.0","source":{"id":"2305.17552","kind":"arxiv","version":2}},"canonical_sha256":"88823b4e05cdb6d13b58a57049e30e24dee4d82c2b5d92900a65211b53def2e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88823b4e05cdb6d13b58a57049e30e24dee4d82c2b5d92900a65211b53def2e6","first_computed_at":"2026-07-05T07:07:37.982918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:37.982918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XlwsOIBVz6ntrFjDkiZ+EtXx7Zh0A0SjZU5DOujbZboI/uL9gc0Q0J5B8ByvEPFAS1XY5i9s9EoDrhHQKdUICw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:37.983432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17552","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8b1ac564128b48108d43854bff28fdae6218f67e3613ae7dce9fa36573ed04a","sha256:4d96d43395e6b5010af367c5c3c121e6ede506136e41092a5d31e38bbcb191c2"],"state_sha256":"af4e8c5c616e882422b7a8bf10fc768ae8b0bdc3d9f54f94415c3ae64afd9576"}