{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:R24MKQRMBHLBST7XRFPN2TOHPB","short_pith_number":"pith:R24MKQRM","schema_version":"1.0","canonical_sha256":"8eb8c5422c09d6194ff7895edd4dc7785e14ebbf7647608bec9d6b2783e1226a","source":{"kind":"arxiv","id":"1908.03568","version":3},"attestation_state":"computed","paper":{"title":"Behaviour Suite for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andre Saraiva, Benjamin Van Roy, Csaba Szepesvari, David Silver, Eren Sezener, Hado van Hasselt, Ian Osband, John Aslanides, Katrina McKinney, Matteo Hessel, Richard Sutton, Satinder Singh, Tor Lattimore, Yotam Doron","submitted_at":"2019-08-09T08:34:08Z","abstract_excerpt":"This paper introduces the Behaviour Suite for Reinforcement Learning, or bsuite for short. bsuite is a collection of carefully-designed experiments that investigate core capabilities of reinforcement learning (RL) agents with two objectives. First, to collect clear, informative and scalable problems that capture key issues in the design of general and efficient learning algorithms. Second, to study agent behaviour through their performance on these shared benchmarks. To complement this effort, we open source github.com/deepmind/bsuite, which automates evaluation and analysis of any agent on bs"},"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":"1908.03568","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-09T08:34:08Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ce99d93c6bf969d29a936a4d2e0c03407b76feada3d3ae2624793341e6f5f3c0","abstract_canon_sha256":"306937d15bef28ad2aa1687b9effae714c9e24b3379602b957cd4362cabf5a4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:44.004433Z","signature_b64":"VqJEPumue9i5yeh2irS2hgaLT9SUdvGg0xQK683JaOhQOCdPleU07N/O120ZKlr28Rxt+18nG7OKWoHDfEFEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8eb8c5422c09d6194ff7895edd4dc7785e14ebbf7647608bec9d6b2783e1226a","last_reissued_at":"2026-07-05T00:40:44.003876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:44.003876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Behaviour Suite for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andre Saraiva, Benjamin Van Roy, Csaba Szepesvari, David Silver, Eren Sezener, Hado van Hasselt, Ian Osband, John Aslanides, Katrina McKinney, Matteo Hessel, Richard Sutton, Satinder Singh, Tor Lattimore, Yotam Doron","submitted_at":"2019-08-09T08:34:08Z","abstract_excerpt":"This paper introduces the Behaviour Suite for Reinforcement Learning, or bsuite for short. bsuite is a collection of carefully-designed experiments that investigate core capabilities of reinforcement learning (RL) agents with two objectives. First, to collect clear, informative and scalable problems that capture key issues in the design of general and efficient learning algorithms. Second, to study agent behaviour through their performance on these shared benchmarks. To complement this effort, we open source github.com/deepmind/bsuite, which automates evaluation and analysis of any agent on bs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03568","kind":"arxiv","version":3},"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/1908.03568/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1908.03568","created_at":"2026-07-05T00:40:44.003944+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.03568v3","created_at":"2026-07-05T00:40:44.003944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03568","created_at":"2026-07-05T00:40:44.003944+00:00"},{"alias_kind":"pith_short_12","alias_value":"R24MKQRMBHLB","created_at":"2026-07-05T00:40:44.003944+00:00"},{"alias_kind":"pith_short_16","alias_value":"R24MKQRMBHLBST7X","created_at":"2026-07-05T00:40:44.003944+00:00"},{"alias_kind":"pith_short_8","alias_value":"R24MKQRM","created_at":"2026-07-05T00:40:44.003944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.20349","citing_title":"Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behavior","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2502.20349","citing_title":"Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behavior","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11694","citing_title":"Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"1911.01547","citing_title":"On the Measure of Intelligence","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2407.17032","citing_title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2301.04104","citing_title":"Mastering Diverse Domains through World Models","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R24MKQRMBHLBST7XRFPN2TOHPB","json":"https://pith.science/pith/R24MKQRMBHLBST7XRFPN2TOHPB.json","graph_json":"https://pith.science/api/pith-number/R24MKQRMBHLBST7XRFPN2TOHPB/graph.json","events_json":"https://pith.science/api/pith-number/R24MKQRMBHLBST7XRFPN2TOHPB/events.json","paper":"https://pith.science/paper/R24MKQRM"},"agent_actions":{"view_html":"https://pith.science/pith/R24MKQRMBHLBST7XRFPN2TOHPB","download_json":"https://pith.science/pith/R24MKQRMBHLBST7XRFPN2TOHPB.json","view_paper":"https://pith.science/paper/R24MKQRM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.03568&json=true","fetch_graph":"https://pith.science/api/pith-number/R24MKQRMBHLBST7XRFPN2TOHPB/graph.json","fetch_events":"https://pith.science/api/pith-number/R24MKQRMBHLBST7XRFPN2TOHPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R24MKQRMBHLBST7XRFPN2TOHPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R24MKQRMBHLBST7XRFPN2TOHPB/action/storage_attestation","attest_author":"https://pith.science/pith/R24MKQRMBHLBST7XRFPN2TOHPB/action/author_attestation","sign_citation":"https://pith.science/pith/R24MKQRMBHLBST7XRFPN2TOHPB/action/citation_signature","submit_replication":"https://pith.science/pith/R24MKQRMBHLBST7XRFPN2TOHPB/action/replication_record"}},"created_at":"2026-07-05T00:40:44.003944+00:00","updated_at":"2026-07-05T00:40:44.003944+00:00"}