{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FAXVPNCD55CMUUKSMJMUXLFFL5","short_pith_number":"pith:FAXVPNCD","canonical_record":{"source":{"id":"2210.02087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-05T08:26:49Z","cross_cats_sorted":[],"title_canon_sha256":"7806a524c06ad9e2896baaf3d8e887ff5c58129545a2fcc788a522a65c1ea62d","abstract_canon_sha256":"ae2e6b66746bafe751d51f08bb68fa1069958c55b6d80e6ead3095a9bc54ee17"},"schema_version":"1.0"},"canonical_sha256":"282f57b443ef44ca515262594baca55f4c42d007c3ebb89592439710cbc6dcfb","source":{"kind":"arxiv","id":"2210.02087","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02087","created_at":"2026-07-05T05:03:43Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02087v1","created_at":"2026-07-05T05:03:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02087","created_at":"2026-07-05T05:03:43Z"},{"alias_kind":"pith_short_12","alias_value":"FAXVPNCD55CM","created_at":"2026-07-05T05:03:43Z"},{"alias_kind":"pith_short_16","alias_value":"FAXVPNCD55CMUUKS","created_at":"2026-07-05T05:03:43Z"},{"alias_kind":"pith_short_8","alias_value":"FAXVPNCD","created_at":"2026-07-05T05:03:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FAXVPNCD55CMUUKSMJMUXLFFL5","target":"record","payload":{"canonical_record":{"source":{"id":"2210.02087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-05T08:26:49Z","cross_cats_sorted":[],"title_canon_sha256":"7806a524c06ad9e2896baaf3d8e887ff5c58129545a2fcc788a522a65c1ea62d","abstract_canon_sha256":"ae2e6b66746bafe751d51f08bb68fa1069958c55b6d80e6ead3095a9bc54ee17"},"schema_version":"1.0"},"canonical_sha256":"282f57b443ef44ca515262594baca55f4c42d007c3ebb89592439710cbc6dcfb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:43.085876Z","signature_b64":"1KlUUkgXqVqFSVgIJRzLh22j7oIisyEF8Fjo/VHXZcrlZguuc4jXmCZ9SG8Xj0H9lYKAJhalCYCn/I/0aFv8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"282f57b443ef44ca515262594baca55f4c42d007c3ebb89592439710cbc6dcfb","last_reissued_at":"2026-07-05T05:03:43.085467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:43.085467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.02087","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":"2026-07-05T05:03:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+qy20q9s5xqAIwoNKWrPRA2XTFNhAzpwYICLy/ItiMhqvKHVKeu+cI4Klg+XHGt6MCeZM9UZW4UG39OOvXp2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:14:36.362117Z"},"content_sha256":"55c02415086db7c1cf07712169947d29c683dd3e86deb4ebd6795f2272b4db84","schema_version":"1.0","event_id":"sha256:55c02415086db7c1cf07712169947d29c683dd3e86deb4ebd6795f2272b4db84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FAXVPNCD55CMUUKSMJMUXLFFL5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration and Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Debabrota Basu (CRIStAL), Odalric-Ambrym Maillard (CRIStAL), Reda Ouhamma (CRIStAL)","submitted_at":"2022-10-05T08:26:49Z","abstract_excerpt":"We study the problem of episodic reinforcement learning in continuous state-action spaces with unknown rewards and transitions. Specifically, we consider the setting where the rewards and transitions are modeled using parametric bilinear exponential families. We propose an algorithm, BEF-RLSVI, that a) uses penalized maximum likelihood estimators to learn the unknown parameters, b) injects a calibrated Gaussian noise in the parameter of rewards to ensure exploration, and c) leverages linearity of the exponential family with respect to an underlying RKHS to perform tractable planning. We furthe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02087","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/2210.02087/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":"2026-07-05T05:03:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mn1qHqg7ZiuikbEYNVPOILyQ076x7XMBBOiVqKYakmt/THz7qMZxxgdmRKChjNWRKBuDvnzrv/A8byLSg3g9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:14:36.362771Z"},"content_sha256":"4e8d525871c81fbcc91d9186bfd1bf90d241596471fb2b7a01bdd1530d477465","schema_version":"1.0","event_id":"sha256:4e8d525871c81fbcc91d9186bfd1bf90d241596471fb2b7a01bdd1530d477465"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FAXVPNCD55CMUUKSMJMUXLFFL5/bundle.json","state_url":"https://pith.science/pith/FAXVPNCD55CMUUKSMJMUXLFFL5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FAXVPNCD55CMUUKSMJMUXLFFL5/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":"2026-08-11T20:14:36Z","links":{"resolver":"https://pith.science/pith/FAXVPNCD55CMUUKSMJMUXLFFL5","bundle":"https://pith.science/pith/FAXVPNCD55CMUUKSMJMUXLFFL5/bundle.json","state":"https://pith.science/pith/FAXVPNCD55CMUUKSMJMUXLFFL5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FAXVPNCD55CMUUKSMJMUXLFFL5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FAXVPNCD55CMUUKSMJMUXLFFL5","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":"ae2e6b66746bafe751d51f08bb68fa1069958c55b6d80e6ead3095a9bc54ee17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-05T08:26:49Z","title_canon_sha256":"7806a524c06ad9e2896baaf3d8e887ff5c58129545a2fcc788a522a65c1ea62d"},"schema_version":"1.0","source":{"id":"2210.02087","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02087","created_at":"2026-07-05T05:03:43Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02087v1","created_at":"2026-07-05T05:03:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02087","created_at":"2026-07-05T05:03:43Z"},{"alias_kind":"pith_short_12","alias_value":"FAXVPNCD55CM","created_at":"2026-07-05T05:03:43Z"},{"alias_kind":"pith_short_16","alias_value":"FAXVPNCD55CMUUKS","created_at":"2026-07-05T05:03:43Z"},{"alias_kind":"pith_short_8","alias_value":"FAXVPNCD","created_at":"2026-07-05T05:03:43Z"}],"graph_snapshots":[{"event_id":"sha256:4e8d525871c81fbcc91d9186bfd1bf90d241596471fb2b7a01bdd1530d477465","target":"graph","created_at":"2026-07-05T05:03:43Z","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/2210.02087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of episodic reinforcement learning in continuous state-action spaces with unknown rewards and transitions. Specifically, we consider the setting where the rewards and transitions are modeled using parametric bilinear exponential families. We propose an algorithm, BEF-RLSVI, that a) uses penalized maximum likelihood estimators to learn the unknown parameters, b) injects a calibrated Gaussian noise in the parameter of rewards to ensure exploration, and c) leverages linearity of the exponential family with respect to an underlying RKHS to perform tractable planning. We furthe","authors_text":"Debabrota Basu (CRIStAL), Odalric-Ambrym Maillard (CRIStAL), Reda Ouhamma (CRIStAL)","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-05T08:26:49Z","title":"Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration and Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02087","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":"sha256:55c02415086db7c1cf07712169947d29c683dd3e86deb4ebd6795f2272b4db84","target":"record","created_at":"2026-07-05T05:03:43Z","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":"ae2e6b66746bafe751d51f08bb68fa1069958c55b6d80e6ead3095a9bc54ee17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-05T08:26:49Z","title_canon_sha256":"7806a524c06ad9e2896baaf3d8e887ff5c58129545a2fcc788a522a65c1ea62d"},"schema_version":"1.0","source":{"id":"2210.02087","kind":"arxiv","version":1}},"canonical_sha256":"282f57b443ef44ca515262594baca55f4c42d007c3ebb89592439710cbc6dcfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"282f57b443ef44ca515262594baca55f4c42d007c3ebb89592439710cbc6dcfb","first_computed_at":"2026-07-05T05:03:43.085467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:43.085467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1KlUUkgXqVqFSVgIJRzLh22j7oIisyEF8Fjo/VHXZcrlZguuc4jXmCZ9SG8Xj0H9lYKAJhalCYCn/I/0aFv8Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:43.085876Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.02087","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55c02415086db7c1cf07712169947d29c683dd3e86deb4ebd6795f2272b4db84","sha256:4e8d525871c81fbcc91d9186bfd1bf90d241596471fb2b7a01bdd1530d477465"],"state_sha256":"a50ddfa7790e37673a1d8447ea85f1e0bd47f29a4c822b9bfebba248092d65dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZTVQwKgEPBTWF0M9JOX8akt5BV7NOLX7f2ZEMJ6pdBdZc3JxhKuwcPBgDWfs7gGVp+vTTDb/DjW/3uoHRGsAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T20:14:36.369465Z","bundle_sha256":"a6d9645232df5ae6fabace79f076eb166b04d7cf6dc83adc2fb4883f36308286"}}