{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DISNIHVAZGUJIYH42TS5FPAKFJ","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":"a381c5e44caac10a442c086513d2f4ae3b7ffa5fb9113398a3b985fc97fb111c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-07T07:59:50Z","title_canon_sha256":"0516ecdaf5c2f78cb25bcad36de8e38f6a332a88cd8a4872a68b77aaac92688e"},"schema_version":"1.0","source":{"id":"2110.03244","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03244","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03244v4","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03244","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"DISNIHVAZGUJ","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"DISNIHVAZGUJIYH4","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"DISNIHVA","created_at":"2026-07-05T04:04:42Z"}],"graph_snapshots":[{"event_id":"sha256:ce495074794bdcd14410cad5aadf1d4caadb3ac12fbbf9b64fa7568510f0be11","target":"graph","created_at":"2026-07-05T04:04:42Z","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/2110.03244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jiachen Hu, Lin F. Yang, Liwei Wang, Xiaoyu Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-07T07:59:50Z","title":"Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03244","kind":"arxiv","version":4},"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":"sha256:66e6896e053b6a271ac64aae7d35453a381f7d1f85d07979380cfbabaed57c69","target":"record","created_at":"2026-07-05T04:04:42Z","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":"a381c5e44caac10a442c086513d2f4ae3b7ffa5fb9113398a3b985fc97fb111c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-07T07:59:50Z","title_canon_sha256":"0516ecdaf5c2f78cb25bcad36de8e38f6a332a88cd8a4872a68b77aaac92688e"},"schema_version":"1.0","source":{"id":"2110.03244","kind":"arxiv","version":4}},"canonical_sha256":"1a24d41ea0c9a89460fcd4e5d2bc0a2a74cccbcb59bfd94813bd9f22160424b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a24d41ea0c9a89460fcd4e5d2bc0a2a74cccbcb59bfd94813bd9f22160424b7","first_computed_at":"2026-07-05T04:04:42.076049Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:04:42.076049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qg3Z61UPx6ss4CV48lD256mWoldLVmF0JW4pGSOdhYmNDB1JaLxPwAwbbYSdJTNoiPp5h9opBLwXz4mY15vcBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:04:42.076425Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.03244","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66e6896e053b6a271ac64aae7d35453a381f7d1f85d07979380cfbabaed57c69","sha256:ce495074794bdcd14410cad5aadf1d4caadb3ac12fbbf9b64fa7568510f0be11"],"state_sha256":"78e9a313074a2f7e84b7dc429d7cba85b0a523c00dc96fad7924338b63c87316"}