{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UWMCWECCWX57OYYBD67GGTBK3L","short_pith_number":"pith:UWMCWECC","schema_version":"1.0","canonical_sha256":"a5982b1042b5fbf763011fbe634c2adaf47957c05db3d9eb66238e9e82a70e94","source":{"kind":"arxiv","id":"2102.01514","version":1},"attestation_state":"computed","paper":{"title":"Metrics and continuity in reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Charline Le Lan, Marc G. Bellemare, Pablo Samuel Castro","submitted_at":"2021-02-02T14:30:41Z","abstract_excerpt":"In most practical applications of reinforcement learning, it is untenable to maintain direct estimates for individual states; in continuous-state systems, it is impossible. Instead, researchers often leverage state similarity (whether explicitly or implicitly) to build models that can generalize well from a limited set of samples. The notion of state similarity used, and the neighbourhoods and topologies they induce, is thus of crucial importance, as it will directly affect the performance of the algorithms. Indeed, a number of recent works introduce algorithms assuming the existence of \"well-"},"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":"2102.01514","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-02T14:30:41Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e8b9c53ff75e0168f8a63f23e67359f93accf3b9d29f080b7205d3d091083e45","abstract_canon_sha256":"e528127e51d18bf0bc578b8185f305062c7f07783c7fb79ace72a597f3ddddff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:11:31.259877Z","signature_b64":"KYmfJN041cEYcn0OqYR+HI4EFSvQHS/uIWk1O/a+gtNDBu9FMNIhpvkDQnRK/yYc85+WeKzIig29L91C5hdqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5982b1042b5fbf763011fbe634c2adaf47957c05db3d9eb66238e9e82a70e94","last_reissued_at":"2026-07-05T02:11:31.259485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:11:31.259485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metrics and continuity in reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Charline Le Lan, Marc G. Bellemare, Pablo Samuel Castro","submitted_at":"2021-02-02T14:30:41Z","abstract_excerpt":"In most practical applications of reinforcement learning, it is untenable to maintain direct estimates for individual states; in continuous-state systems, it is impossible. Instead, researchers often leverage state similarity (whether explicitly or implicitly) to build models that can generalize well from a limited set of samples. The notion of state similarity used, and the neighbourhoods and topologies they induce, is thus of crucial importance, as it will directly affect the performance of the algorithms. Indeed, a number of recent works introduce algorithms assuming the existence of \"well-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01514","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/2102.01514/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":"2102.01514","created_at":"2026-07-05T02:11:31.259551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.01514v1","created_at":"2026-07-05T02:11:31.259551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01514","created_at":"2026-07-05T02:11:31.259551+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWMCWECCWX57","created_at":"2026-07-05T02:11:31.259551+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWMCWECCWX57OYYB","created_at":"2026-07-05T02:11:31.259551+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWMCWECC","created_at":"2026-07-05T02:11:31.259551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14564","citing_title":"Bellman operator convergence enhancements in reinforcement learning algorithms","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UWMCWECCWX57OYYBD67GGTBK3L","json":"https://pith.science/pith/UWMCWECCWX57OYYBD67GGTBK3L.json","graph_json":"https://pith.science/api/pith-number/UWMCWECCWX57OYYBD67GGTBK3L/graph.json","events_json":"https://pith.science/api/pith-number/UWMCWECCWX57OYYBD67GGTBK3L/events.json","paper":"https://pith.science/paper/UWMCWECC"},"agent_actions":{"view_html":"https://pith.science/pith/UWMCWECCWX57OYYBD67GGTBK3L","download_json":"https://pith.science/pith/UWMCWECCWX57OYYBD67GGTBK3L.json","view_paper":"https://pith.science/paper/UWMCWECC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.01514&json=true","fetch_graph":"https://pith.science/api/pith-number/UWMCWECCWX57OYYBD67GGTBK3L/graph.json","fetch_events":"https://pith.science/api/pith-number/UWMCWECCWX57OYYBD67GGTBK3L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWMCWECCWX57OYYBD67GGTBK3L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWMCWECCWX57OYYBD67GGTBK3L/action/storage_attestation","attest_author":"https://pith.science/pith/UWMCWECCWX57OYYBD67GGTBK3L/action/author_attestation","sign_citation":"https://pith.science/pith/UWMCWECCWX57OYYBD67GGTBK3L/action/citation_signature","submit_replication":"https://pith.science/pith/UWMCWECCWX57OYYBD67GGTBK3L/action/replication_record"}},"created_at":"2026-07-05T02:11:31.259551+00:00","updated_at":"2026-07-05T02:11:31.259551+00:00"}