{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:O35TSYQBNCH5JBMDT7TIXS55TA","short_pith_number":"pith:O35TSYQB","schema_version":"1.0","canonical_sha256":"76fb396201688fd485839fe68bcbbd9832b5898ad83f98737a1612157a02492d","source":{"kind":"arxiv","id":"2310.07811","version":2},"attestation_state":"computed","paper":{"title":"Online RL in Linearly $q^\\pi$-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andr\\'as Gy\\\"orgy, Csaba Szepesv\\'ari, Gell\\'ert Weisz","submitted_at":"2023-10-11T18:50:25Z","abstract_excerpt":"We consider online reinforcement learning (RL) in episodic Markov decision processes (MDPs) under the linear $q^\\pi$-realizability assumption, where it is assumed that the action-values of all policies can be expressed as linear functions of state-action features. This class is known to be more general than linear MDPs, where the transition kernel and the reward function are assumed to be linear functions of the feature vectors. As our first contribution, we show that the difference between the two classes is the presence of states in linearly $q^\\pi$-realizable MDPs where for any policy, all "},"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":"2310.07811","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T18:50:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"741169cccb022d6bf980283c3223323913e7dfb45261530bea4bf110de86639f","abstract_canon_sha256":"2467054ee8cb024ebec7483dd2695d6718312cb40824a4f968143b52d983263a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:17.903121Z","signature_b64":"VwbJKDl2+ohjpN+aZGckhvgLaq5dMv6imQxyZOpmB2sj5osySSP+6Kp0QYhzkjNfaUdN4omJ0LCcQhyujyeoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76fb396201688fd485839fe68bcbbd9832b5898ad83f98737a1612157a02492d","last_reissued_at":"2026-07-05T07:26:17.902620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:17.902620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online RL in Linearly $q^\\pi$-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andr\\'as Gy\\\"orgy, Csaba Szepesv\\'ari, Gell\\'ert Weisz","submitted_at":"2023-10-11T18:50:25Z","abstract_excerpt":"We consider online reinforcement learning (RL) in episodic Markov decision processes (MDPs) under the linear $q^\\pi$-realizability assumption, where it is assumed that the action-values of all policies can be expressed as linear functions of state-action features. This class is known to be more general than linear MDPs, where the transition kernel and the reward function are assumed to be linear functions of the feature vectors. As our first contribution, we show that the difference between the two classes is the presence of states in linearly $q^\\pi$-realizable MDPs where for any policy, all "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07811","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/2310.07811/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":"2310.07811","created_at":"2026-07-05T07:26:17.902687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07811v2","created_at":"2026-07-05T07:26:17.902687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07811","created_at":"2026-07-05T07:26:17.902687+00:00"},{"alias_kind":"pith_short_12","alias_value":"O35TSYQBNCH5","created_at":"2026-07-05T07:26:17.902687+00:00"},{"alias_kind":"pith_short_16","alias_value":"O35TSYQBNCH5JBMD","created_at":"2026-07-05T07:26:17.902687+00:00"},{"alias_kind":"pith_short_8","alias_value":"O35TSYQB","created_at":"2026-07-05T07:26:17.902687+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/O35TSYQBNCH5JBMDT7TIXS55TA","json":"https://pith.science/pith/O35TSYQBNCH5JBMDT7TIXS55TA.json","graph_json":"https://pith.science/api/pith-number/O35TSYQBNCH5JBMDT7TIXS55TA/graph.json","events_json":"https://pith.science/api/pith-number/O35TSYQBNCH5JBMDT7TIXS55TA/events.json","paper":"https://pith.science/paper/O35TSYQB"},"agent_actions":{"view_html":"https://pith.science/pith/O35TSYQBNCH5JBMDT7TIXS55TA","download_json":"https://pith.science/pith/O35TSYQBNCH5JBMDT7TIXS55TA.json","view_paper":"https://pith.science/paper/O35TSYQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07811&json=true","fetch_graph":"https://pith.science/api/pith-number/O35TSYQBNCH5JBMDT7TIXS55TA/graph.json","fetch_events":"https://pith.science/api/pith-number/O35TSYQBNCH5JBMDT7TIXS55TA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O35TSYQBNCH5JBMDT7TIXS55TA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O35TSYQBNCH5JBMDT7TIXS55TA/action/storage_attestation","attest_author":"https://pith.science/pith/O35TSYQBNCH5JBMDT7TIXS55TA/action/author_attestation","sign_citation":"https://pith.science/pith/O35TSYQBNCH5JBMDT7TIXS55TA/action/citation_signature","submit_replication":"https://pith.science/pith/O35TSYQBNCH5JBMDT7TIXS55TA/action/replication_record"}},"created_at":"2026-07-05T07:26:17.902687+00:00","updated_at":"2026-07-05T07:26:17.902687+00:00"}