{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IN42KQMPN6X4THLRH5U4YCRM3O","short_pith_number":"pith:IN42KQMP","schema_version":"1.0","canonical_sha256":"4379a5418f6fafc99d713f69cc0a2cdb9902cce376d24b5122795ed7c4aee56e","source":{"kind":"arxiv","id":"2101.00494","version":1},"attestation_state":"computed","paper":{"title":"A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lin F. Yang, Minbo Gao, Simon S. Du, Tianle Xie","submitted_at":"2021-01-02T18:41:27Z","abstract_excerpt":"Many real-world applications, such as those in medical domains, recommendation systems, etc, can be formulated as large state space reinforcement learning problems with only a small budget of the number of policy changes, i.e., low switching cost. This paper focuses on the linear Markov Decision Process (MDP) recently studied in [Yang et al 2019, Jin et al 2020] where the linear function approximation is used for generalization on the large state space. We present the first algorithm for linear MDP with a low switching cost. Our algorithm achieves an $\\widetilde{O}\\left(\\sqrt{d^3H^4K}\\right)$ "},"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":"2101.00494","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-02T18:41:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5a18a54dc7cd01586165479025a271f806e1fc22395bd97e6af8e3986e38b5b8","abstract_canon_sha256":"dd574942fe7a956cb1b81cb9c76677b2fb75f66cb5a0ea2415e1fd9ed6ee2ef4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:04:19.108688Z","signature_b64":"TQvfvo1iZwztg7OnZANlrP6ad52iI+B0sAAWF1zsiiaFAeDWIbROBb+iIDxp7QYP8gixigOt8lyHXhSM/keyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4379a5418f6fafc99d713f69cc0a2cdb9902cce376d24b5122795ed7c4aee56e","last_reissued_at":"2026-07-05T02:04:19.108208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:04:19.108208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lin F. Yang, Minbo Gao, Simon S. Du, Tianle Xie","submitted_at":"2021-01-02T18:41:27Z","abstract_excerpt":"Many real-world applications, such as those in medical domains, recommendation systems, etc, can be formulated as large state space reinforcement learning problems with only a small budget of the number of policy changes, i.e., low switching cost. This paper focuses on the linear Markov Decision Process (MDP) recently studied in [Yang et al 2019, Jin et al 2020] where the linear function approximation is used for generalization on the large state space. We present the first algorithm for linear MDP with a low switching cost. Our algorithm achieves an $\\widetilde{O}\\left(\\sqrt{d^3H^4K}\\right)$ "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00494","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/2101.00494/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":"2101.00494","created_at":"2026-07-05T02:04:19.108265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.00494v1","created_at":"2026-07-05T02:04:19.108265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00494","created_at":"2026-07-05T02:04:19.108265+00:00"},{"alias_kind":"pith_short_12","alias_value":"IN42KQMPN6X4","created_at":"2026-07-05T02:04:19.108265+00:00"},{"alias_kind":"pith_short_16","alias_value":"IN42KQMPN6X4THLR","created_at":"2026-07-05T02:04:19.108265+00:00"},{"alias_kind":"pith_short_8","alias_value":"IN42KQMP","created_at":"2026-07-05T02:04:19.108265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00393","citing_title":"Model-Based Reinforcement Learning with Double Oracle Efficiency in Policy Optimization and Offline Estimation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IN42KQMPN6X4THLRH5U4YCRM3O","json":"https://pith.science/pith/IN42KQMPN6X4THLRH5U4YCRM3O.json","graph_json":"https://pith.science/api/pith-number/IN42KQMPN6X4THLRH5U4YCRM3O/graph.json","events_json":"https://pith.science/api/pith-number/IN42KQMPN6X4THLRH5U4YCRM3O/events.json","paper":"https://pith.science/paper/IN42KQMP"},"agent_actions":{"view_html":"https://pith.science/pith/IN42KQMPN6X4THLRH5U4YCRM3O","download_json":"https://pith.science/pith/IN42KQMPN6X4THLRH5U4YCRM3O.json","view_paper":"https://pith.science/paper/IN42KQMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.00494&json=true","fetch_graph":"https://pith.science/api/pith-number/IN42KQMPN6X4THLRH5U4YCRM3O/graph.json","fetch_events":"https://pith.science/api/pith-number/IN42KQMPN6X4THLRH5U4YCRM3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IN42KQMPN6X4THLRH5U4YCRM3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IN42KQMPN6X4THLRH5U4YCRM3O/action/storage_attestation","attest_author":"https://pith.science/pith/IN42KQMPN6X4THLRH5U4YCRM3O/action/author_attestation","sign_citation":"https://pith.science/pith/IN42KQMPN6X4THLRH5U4YCRM3O/action/citation_signature","submit_replication":"https://pith.science/pith/IN42KQMPN6X4THLRH5U4YCRM3O/action/replication_record"}},"created_at":"2026-07-05T02:04:19.108265+00:00","updated_at":"2026-07-05T02:04:19.108265+00:00"}