{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DISNIHVAZGUJIYH42TS5FPAKFJ","short_pith_number":"pith:DISNIHVA","schema_version":"1.0","canonical_sha256":"1a24d41ea0c9a89460fcd4e5d2bc0a2a74cccbcb59bfd94813bd9f22160424b7","source":{"kind":"arxiv","id":"2110.03244","version":4},"attestation_state":"computed","paper":{"title":"Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiachen Hu, Lin F. Yang, Liwei Wang, Xiaoyu Chen","submitted_at":"2021-10-07T07:59:50Z","abstract_excerpt":"Although model-based reinforcement learning (RL) approaches are considered more sample efficient, existing algorithms are usually relying on sophisticated planning algorithm to couple tightly with the model-learning procedure. Hence the learned models may lack the ability of being re-used with more specialized planners. In this paper we address this issue and provide approaches to learn an RL model efficiently without the guidance of a reward signal. In particular, we take a plug-in solver approach, where we focus on learning a model in the exploration phase and demand that \\emph{any planning "},"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":"2110.03244","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-07T07:59:50Z","cross_cats_sorted":[],"title_canon_sha256":"0516ecdaf5c2f78cb25bcad36de8e38f6a332a88cd8a4872a68b77aaac92688e","abstract_canon_sha256":"a381c5e44caac10a442c086513d2f4ae3b7ffa5fb9113398a3b985fc97fb111c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:42.076425Z","signature_b64":"qg3Z61UPx6ss4CV48lD256mWoldLVmF0JW4pGSOdhYmNDB1JaLxPwAwbbYSdJTNoiPp5h9opBLwXz4mY15vcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a24d41ea0c9a89460fcd4e5d2bc0a2a74cccbcb59bfd94813bd9f22160424b7","last_reissued_at":"2026-07-05T04:04:42.076049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:42.076049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiachen Hu, Lin F. Yang, Liwei Wang, Xiaoyu Chen","submitted_at":"2021-10-07T07:59:50Z","abstract_excerpt":"Although model-based reinforcement learning (RL) approaches are considered more sample efficient, existing algorithms are usually relying on sophisticated planning algorithm to couple tightly with the model-learning procedure. Hence the learned models may lack the ability of being re-used with more specialized planners. In this paper we address this issue and provide approaches to learn an RL model efficiently without the guidance of a reward signal. In particular, we take a plug-in solver approach, where we focus on learning a model in the exploration phase and demand that \\emph{any planning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03244","kind":"arxiv","version":4},"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/2110.03244/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":"2110.03244","created_at":"2026-07-05T04:04:42.076105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03244v4","created_at":"2026-07-05T04:04:42.076105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03244","created_at":"2026-07-05T04:04:42.076105+00:00"},{"alias_kind":"pith_short_12","alias_value":"DISNIHVAZGUJ","created_at":"2026-07-05T04:04:42.076105+00:00"},{"alias_kind":"pith_short_16","alias_value":"DISNIHVAZGUJIYH4","created_at":"2026-07-05T04:04:42.076105+00:00"},{"alias_kind":"pith_short_8","alias_value":"DISNIHVA","created_at":"2026-07-05T04:04:42.076105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09940","citing_title":"The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability","ref_index":2011,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DISNIHVAZGUJIYH42TS5FPAKFJ","json":"https://pith.science/pith/DISNIHVAZGUJIYH42TS5FPAKFJ.json","graph_json":"https://pith.science/api/pith-number/DISNIHVAZGUJIYH42TS5FPAKFJ/graph.json","events_json":"https://pith.science/api/pith-number/DISNIHVAZGUJIYH42TS5FPAKFJ/events.json","paper":"https://pith.science/paper/DISNIHVA"},"agent_actions":{"view_html":"https://pith.science/pith/DISNIHVAZGUJIYH42TS5FPAKFJ","download_json":"https://pith.science/pith/DISNIHVAZGUJIYH42TS5FPAKFJ.json","view_paper":"https://pith.science/paper/DISNIHVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03244&json=true","fetch_graph":"https://pith.science/api/pith-number/DISNIHVAZGUJIYH42TS5FPAKFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DISNIHVAZGUJIYH42TS5FPAKFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DISNIHVAZGUJIYH42TS5FPAKFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DISNIHVAZGUJIYH42TS5FPAKFJ/action/storage_attestation","attest_author":"https://pith.science/pith/DISNIHVAZGUJIYH42TS5FPAKFJ/action/author_attestation","sign_citation":"https://pith.science/pith/DISNIHVAZGUJIYH42TS5FPAKFJ/action/citation_signature","submit_replication":"https://pith.science/pith/DISNIHVAZGUJIYH42TS5FPAKFJ/action/replication_record"}},"created_at":"2026-07-05T04:04:42.076105+00:00","updated_at":"2026-07-05T04:04:42.076105+00:00"}