{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DISNIHVAZGUJIYH42TS5FPAKFJ","short_pith_number":"pith:DISNIHVA","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"},"canonical_sha256":"1a24d41ea0c9a89460fcd4e5d2bc0a2a74cccbcb59bfd94813bd9f22160424b7","source":{"kind":"arxiv","id":"2110.03244","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DISNIHVAZGUJIYH42TS5FPAKFJ","target":"record","payload":{"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"},"canonical_sha256":"1a24d41ea0c9a89460fcd4e5d2bc0a2a74cccbcb59bfd94813bd9f22160424b7","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"},"source_kind":"arxiv","source_id":"2110.03244","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NwnLHNXBD7NnXoys9/U+6W4W9nCLHV1KMaTrinPX5JT4dz8WHEE/Gow5Fx56T4u+s9C7jcQwT2KIpJEB9XBvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:21:45.331213Z"},"content_sha256":"66e6896e053b6a271ac64aae7d35453a381f7d1f85d07979380cfbabaed57c69","schema_version":"1.0","event_id":"sha256:66e6896e053b6a271ac64aae7d35453a381f7d1f85d07979380cfbabaed57c69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DISNIHVAZGUJIYH42TS5FPAKFJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HZRxae7kkuhM4RlSUR9yNNzykHYpaKO3HxoeaEsMAXceE7jik9hPPhLdUz5XWVa7JgQeSoEYPdaCOGp9RcCnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:21:45.331784Z"},"content_sha256":"ce495074794bdcd14410cad5aadf1d4caadb3ac12fbbf9b64fa7568510f0be11","schema_version":"1.0","event_id":"sha256:ce495074794bdcd14410cad5aadf1d4caadb3ac12fbbf9b64fa7568510f0be11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DISNIHVAZGUJIYH42TS5FPAKFJ/bundle.json","state_url":"https://pith.science/pith/DISNIHVAZGUJIYH42TS5FPAKFJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DISNIHVAZGUJIYH42TS5FPAKFJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T00:21:45Z","links":{"resolver":"https://pith.science/pith/DISNIHVAZGUJIYH42TS5FPAKFJ","bundle":"https://pith.science/pith/DISNIHVAZGUJIYH42TS5FPAKFJ/bundle.json","state":"https://pith.science/pith/DISNIHVAZGUJIYH42TS5FPAKFJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DISNIHVAZGUJIYH42TS5FPAKFJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5WuFEc6JOlWHxzUOvWDya+B2PykWIE1kJT6Vgtv4ovs+lzAp+xHHTD2LMQQCmKAmd6ENXpDp15CAIVOAEhEXBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:21:45.336309Z","bundle_sha256":"c835d70c502e21aec2eed0d11b187c00e1612cf382437cf451c2e776cf2bce07"}}