{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:MPZUWQPR7K5PFCYJURZNKQZVGO","short_pith_number":"pith:MPZUWQPR","schema_version":"1.0","canonical_sha256":"63f34b41f1fabaf28b09a472d5433533806a905ed698588be785da083400d771","source":{"kind":"arxiv","id":"1509.04064","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking for Bayesian Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adrien Couetoux, Damien Ernst, Michael Castronovo, Raphael Fonteneau","submitted_at":"2015-09-14T12:47:52Z","abstract_excerpt":"In the Bayesian Reinforcement Learning (BRL) setting, agents try to maximise the collected rewards while interacting with their environment while using some prior knowledge that is accessed beforehand. Many BRL algorithms have already been proposed, but even though a few toy examples exist in the literature, there are still no extensive or rigorous benchmarks to compare them. The paper addresses this problem, and provides a new BRL comparison methodology along with the corresponding open source library. In this methodology, a comparison criterion that measures the performance of algorithms on "},"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":"1509.04064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-09-14T12:47:52Z","cross_cats_sorted":[],"title_canon_sha256":"804e05d2e1a569d68d9f30b6d725267f2ca6a158aaf4d83cbe6b21225a9dc96a","abstract_canon_sha256":"ce47dff63d8fc847340f6a1d9481541a93f1168b0addfb312cf7f86a87cce8f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:51.131411Z","signature_b64":"6QSiAQH2cxOnR5yz0050ZA5lvidx3jvpUQe9yUt1Bp1rqKwmlEsgUiYLghbdmn2vAgeYBL3Zwn3E0ZGIWLOZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63f34b41f1fabaf28b09a472d5433533806a905ed698588be785da083400d771","last_reissued_at":"2026-05-18T01:03:51.130733Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:51.130733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking for Bayesian Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adrien Couetoux, Damien Ernst, Michael Castronovo, Raphael Fonteneau","submitted_at":"2015-09-14T12:47:52Z","abstract_excerpt":"In the Bayesian Reinforcement Learning (BRL) setting, agents try to maximise the collected rewards while interacting with their environment while using some prior knowledge that is accessed beforehand. Many BRL algorithms have already been proposed, but even though a few toy examples exist in the literature, there are still no extensive or rigorous benchmarks to compare them. The paper addresses this problem, and provides a new BRL comparison methodology along with the corresponding open source library. In this methodology, a comparison criterion that measures the performance of algorithms on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.04064","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":""},"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":"1509.04064","created_at":"2026-05-18T01:03:51.130819+00:00"},{"alias_kind":"arxiv_version","alias_value":"1509.04064v1","created_at":"2026-05-18T01:03:51.130819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.04064","created_at":"2026-05-18T01:03:51.130819+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPZUWQPR7K5P","created_at":"2026-05-18T12:29:32.376354+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPZUWQPR7K5PFCYJ","created_at":"2026-05-18T12:29:32.376354+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPZUWQPR","created_at":"2026-05-18T12:29:32.376354+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MPZUWQPR7K5PFCYJURZNKQZVGO","json":"https://pith.science/pith/MPZUWQPR7K5PFCYJURZNKQZVGO.json","graph_json":"https://pith.science/api/pith-number/MPZUWQPR7K5PFCYJURZNKQZVGO/graph.json","events_json":"https://pith.science/api/pith-number/MPZUWQPR7K5PFCYJURZNKQZVGO/events.json","paper":"https://pith.science/paper/MPZUWQPR"},"agent_actions":{"view_html":"https://pith.science/pith/MPZUWQPR7K5PFCYJURZNKQZVGO","download_json":"https://pith.science/pith/MPZUWQPR7K5PFCYJURZNKQZVGO.json","view_paper":"https://pith.science/paper/MPZUWQPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1509.04064&json=true","fetch_graph":"https://pith.science/api/pith-number/MPZUWQPR7K5PFCYJURZNKQZVGO/graph.json","fetch_events":"https://pith.science/api/pith-number/MPZUWQPR7K5PFCYJURZNKQZVGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPZUWQPR7K5PFCYJURZNKQZVGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPZUWQPR7K5PFCYJURZNKQZVGO/action/storage_attestation","attest_author":"https://pith.science/pith/MPZUWQPR7K5PFCYJURZNKQZVGO/action/author_attestation","sign_citation":"https://pith.science/pith/MPZUWQPR7K5PFCYJURZNKQZVGO/action/citation_signature","submit_replication":"https://pith.science/pith/MPZUWQPR7K5PFCYJURZNKQZVGO/action/replication_record"}},"created_at":"2026-05-18T01:03:51.130819+00:00","updated_at":"2026-05-18T01:03:51.130819+00:00"}