{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:YJKF7KUYTWJO2QPBUSALQHFZ66","short_pith_number":"pith:YJKF7KUY","canonical_record":{"source":{"id":"2006.01107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T17:47:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"aa7eeeca4ee93623b7c546f77779f0b09c3bbdb2a64e1ae669ed6d214c366ba1","abstract_canon_sha256":"ca997a0a8e3e01b99b2693dd8d0264c1f379f7d562ece8d8de66386f7a900893"},"schema_version":"1.0"},"canonical_sha256":"c2545faa989d92ed41e1a480b81cb9f79da24f963e610a7277c53619dae3b51e","source":{"kind":"arxiv","id":"2006.01107","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.01107","created_at":"2026-07-05T01:07:08Z"},{"alias_kind":"arxiv_version","alias_value":"2006.01107v1","created_at":"2026-07-05T01:07:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01107","created_at":"2026-07-05T01:07:08Z"},{"alias_kind":"pith_short_12","alias_value":"YJKF7KUYTWJO","created_at":"2026-07-05T01:07:08Z"},{"alias_kind":"pith_short_16","alias_value":"YJKF7KUYTWJO2QPB","created_at":"2026-07-05T01:07:08Z"},{"alias_kind":"pith_short_8","alias_value":"YJKF7KUY","created_at":"2026-07-05T01:07:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:YJKF7KUYTWJO2QPBUSALQHFZ66","target":"record","payload":{"canonical_record":{"source":{"id":"2006.01107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T17:47:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"aa7eeeca4ee93623b7c546f77779f0b09c3bbdb2a64e1ae669ed6d214c366ba1","abstract_canon_sha256":"ca997a0a8e3e01b99b2693dd8d0264c1f379f7d562ece8d8de66386f7a900893"},"schema_version":"1.0"},"canonical_sha256":"c2545faa989d92ed41e1a480b81cb9f79da24f963e610a7277c53619dae3b51e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:08.934805Z","signature_b64":"E+NP2oxrYR5VtLM+dlcHHuxjK0C/F3b1wsAjCJeHRFoCYNolnONs8XtmGTAPT2vkWt0gzYmxJ6m+7TPIKtSuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2545faa989d92ed41e1a480b81cb9f79da24f963e610a7277c53619dae3b51e","last_reissued_at":"2026-07-05T01:07:08.934323Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:08.934323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.01107","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:07:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tS3qa+GKLixxhN57BRfDfngFI2v7X8oICrMv/eCOlsnTCSxFtQ1QGu966oy06Ve4NaAlufiZpiI+pct2f7MlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:36:46.749738Z"},"content_sha256":"cd570c5c04aecfe36603d0d7b4d8f3cb1c8c71da80ffd5be264d67d753f36e01","schema_version":"1.0","event_id":"sha256:cd570c5c04aecfe36603d0d7b4d8f3cb1c8c71da80ffd5be264d67d753f36e01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:YJKF7KUYTWJO2QPBUSALQHFZ66","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-Based Reinforcement Learning with Value-Targeted Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Ayoub, Csaba Szepesvari, Lin F. Yang, Mengdi Wang, Zeyu Jia","submitted_at":"2020-06-01T17:47:53Z","abstract_excerpt":"This paper studies model-based reinforcement learning (RL) for regret minimization. We focus on finite-horizon episodic RL where the transition model $P$ belongs to a known family of models $\\mathcal{P}$, a special case of which is when models in $\\mathcal{P}$ take the form of linear mixtures: $P_{\\theta} = \\sum_{i=1}^{d} \\theta_{i}P_{i}$. We propose a model based RL algorithm that is based on optimism principle: In each episode, the set of models that are `consistent' with the data collected is constructed. The criterion of consistency is based on the total squared error of that the model inc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01107","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/2006.01107/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":"2026-07-05T01:07:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rkaO9QmQt1CZ2e88UgBbUKz9tl3sL3KcamxeE0yz2VYQSdvMnbhMtCAMr/0lKkvOXz3hvg8o+XGPLwr9WPx+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:36:46.750107Z"},"content_sha256":"53983e7fa217c7c70f085570836fedfa78ce31059a508d8743678eae420ca046","schema_version":"1.0","event_id":"sha256:53983e7fa217c7c70f085570836fedfa78ce31059a508d8743678eae420ca046"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YJKF7KUYTWJO2QPBUSALQHFZ66/bundle.json","state_url":"https://pith.science/pith/YJKF7KUYTWJO2QPBUSALQHFZ66/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YJKF7KUYTWJO2QPBUSALQHFZ66/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":"2026-07-07T12:36:46Z","links":{"resolver":"https://pith.science/pith/YJKF7KUYTWJO2QPBUSALQHFZ66","bundle":"https://pith.science/pith/YJKF7KUYTWJO2QPBUSALQHFZ66/bundle.json","state":"https://pith.science/pith/YJKF7KUYTWJO2QPBUSALQHFZ66/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YJKF7KUYTWJO2QPBUSALQHFZ66/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:YJKF7KUYTWJO2QPBUSALQHFZ66","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":"ca997a0a8e3e01b99b2693dd8d0264c1f379f7d562ece8d8de66386f7a900893","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T17:47:53Z","title_canon_sha256":"aa7eeeca4ee93623b7c546f77779f0b09c3bbdb2a64e1ae669ed6d214c366ba1"},"schema_version":"1.0","source":{"id":"2006.01107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.01107","created_at":"2026-07-05T01:07:08Z"},{"alias_kind":"arxiv_version","alias_value":"2006.01107v1","created_at":"2026-07-05T01:07:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01107","created_at":"2026-07-05T01:07:08Z"},{"alias_kind":"pith_short_12","alias_value":"YJKF7KUYTWJO","created_at":"2026-07-05T01:07:08Z"},{"alias_kind":"pith_short_16","alias_value":"YJKF7KUYTWJO2QPB","created_at":"2026-07-05T01:07:08Z"},{"alias_kind":"pith_short_8","alias_value":"YJKF7KUY","created_at":"2026-07-05T01:07:08Z"}],"graph_snapshots":[{"event_id":"sha256:53983e7fa217c7c70f085570836fedfa78ce31059a508d8743678eae420ca046","target":"graph","created_at":"2026-07-05T01:07:08Z","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/2006.01107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies model-based reinforcement learning (RL) for regret minimization. We focus on finite-horizon episodic RL where the transition model $P$ belongs to a known family of models $\\mathcal{P}$, a special case of which is when models in $\\mathcal{P}$ take the form of linear mixtures: $P_{\\theta} = \\sum_{i=1}^{d} \\theta_{i}P_{i}$. We propose a model based RL algorithm that is based on optimism principle: In each episode, the set of models that are `consistent' with the data collected is constructed. The criterion of consistency is based on the total squared error of that the model inc","authors_text":"Alex Ayoub, Csaba Szepesvari, Lin F. Yang, Mengdi Wang, Zeyu Jia","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T17:47:53Z","title":"Model-Based Reinforcement Learning with Value-Targeted Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01107","kind":"arxiv","version":1},"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:cd570c5c04aecfe36603d0d7b4d8f3cb1c8c71da80ffd5be264d67d753f36e01","target":"record","created_at":"2026-07-05T01:07:08Z","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":"ca997a0a8e3e01b99b2693dd8d0264c1f379f7d562ece8d8de66386f7a900893","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-01T17:47:53Z","title_canon_sha256":"aa7eeeca4ee93623b7c546f77779f0b09c3bbdb2a64e1ae669ed6d214c366ba1"},"schema_version":"1.0","source":{"id":"2006.01107","kind":"arxiv","version":1}},"canonical_sha256":"c2545faa989d92ed41e1a480b81cb9f79da24f963e610a7277c53619dae3b51e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2545faa989d92ed41e1a480b81cb9f79da24f963e610a7277c53619dae3b51e","first_computed_at":"2026-07-05T01:07:08.934323Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:07:08.934323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E+NP2oxrYR5VtLM+dlcHHuxjK0C/F3b1wsAjCJeHRFoCYNolnONs8XtmGTAPT2vkWt0gzYmxJ6m+7TPIKtSuBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:07:08.934805Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.01107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd570c5c04aecfe36603d0d7b4d8f3cb1c8c71da80ffd5be264d67d753f36e01","sha256:53983e7fa217c7c70f085570836fedfa78ce31059a508d8743678eae420ca046"],"state_sha256":"2a86741f5a0e36fcd8ebfc93419a03a8f9d2ff50a7536c8f59e87afe1c89e358"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dk/4YJHyi1vUfLIJ51/1Qf/WW0a8vS3Bk74h36ltknfUFHwhO8Eyl2BOrhN9Wqb55DCtZRsyBlt4MtlhzmauDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:36:46.751946Z","bundle_sha256":"a48dc20984d5836a416a2244231dcd62785190b4ac633ae10eb28724967c4341"}}