{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6AJ4FLEXKM6ZSGOOWCX3DBBBXJ","short_pith_number":"pith:6AJ4FLEX","schema_version":"1.0","canonical_sha256":"f013c2ac97533d9919ceb0afb18421ba781a87379eeef83ad521bd95ba0ef2b1","source":{"kind":"arxiv","id":"2003.13350","version":1},"attestation_state":"computed","paper":{"title":"Agent57: Outperforming the Atari Human Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adri\\`a Puigdom\\`enech Badia, Alex Vitvitskyi, Bilal Piot, Charles Blundell, Daniel Guo, Pablo Sprechmann, Steven Kapturowski","submitted_at":"2020-03-30T11:33:16Z","abstract_excerpt":"Atari games have been a long-standing benchmark in the reinforcement learning (RL) community for the past decade. This benchmark was proposed to test general competency of RL algorithms. Previous work has achieved good average performance by doing outstandingly well on many games of the set, but very poorly in several of the most challenging games. We propose Agent57, the first deep RL agent that outperforms the standard human benchmark on all 57 Atari games. To achieve this result, we train a neural network which parameterizes a family of policies ranging from very exploratory to purely explo"},"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":"2003.13350","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T11:33:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e4a4c4085c964b7df959d3a5db1f63fc781c95225a7b2cba33432ced3613f68c","abstract_canon_sha256":"359ab5aa0eda41eb61f0fd0a75b21e21819451d0e734d0dd575ebaf1799f1802"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:22.332821Z","signature_b64":"hNPsThIBpEnDghQ7wPPNloosH2urekuIgtIvv+WZwH1viYr8hD93GPmafd8iqqzYZ4zJTIr1CvA2J2QYH7SmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f013c2ac97533d9919ceb0afb18421ba781a87379eeef83ad521bd95ba0ef2b1","last_reissued_at":"2026-07-05T00:51:22.332322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:22.332322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent57: Outperforming the Atari Human Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adri\\`a Puigdom\\`enech Badia, Alex Vitvitskyi, Bilal Piot, Charles Blundell, Daniel Guo, Pablo Sprechmann, Steven Kapturowski","submitted_at":"2020-03-30T11:33:16Z","abstract_excerpt":"Atari games have been a long-standing benchmark in the reinforcement learning (RL) community for the past decade. This benchmark was proposed to test general competency of RL algorithms. Previous work has achieved good average performance by doing outstandingly well on many games of the set, but very poorly in several of the most challenging games. We propose Agent57, the first deep RL agent that outperforms the standard human benchmark on all 57 Atari games. To achieve this result, we train a neural network which parameterizes a family of policies ranging from very exploratory to purely explo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13350","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/2003.13350/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":"2003.13350","created_at":"2026-07-05T00:51:22.332382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.13350v1","created_at":"2026-07-05T00:51:22.332382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13350","created_at":"2026-07-05T00:51:22.332382+00:00"},{"alias_kind":"pith_short_12","alias_value":"6AJ4FLEXKM6Z","created_at":"2026-07-05T00:51:22.332382+00:00"},{"alias_kind":"pith_short_16","alias_value":"6AJ4FLEXKM6ZSGOO","created_at":"2026-07-05T00:51:22.332382+00:00"},{"alias_kind":"pith_short_8","alias_value":"6AJ4FLEX","created_at":"2026-07-05T00:51:22.332382+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2010.02193","citing_title":"Mastering Atari with Discrete World Models","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6AJ4FLEXKM6ZSGOOWCX3DBBBXJ","json":"https://pith.science/pith/6AJ4FLEXKM6ZSGOOWCX3DBBBXJ.json","graph_json":"https://pith.science/api/pith-number/6AJ4FLEXKM6ZSGOOWCX3DBBBXJ/graph.json","events_json":"https://pith.science/api/pith-number/6AJ4FLEXKM6ZSGOOWCX3DBBBXJ/events.json","paper":"https://pith.science/paper/6AJ4FLEX"},"agent_actions":{"view_html":"https://pith.science/pith/6AJ4FLEXKM6ZSGOOWCX3DBBBXJ","download_json":"https://pith.science/pith/6AJ4FLEXKM6ZSGOOWCX3DBBBXJ.json","view_paper":"https://pith.science/paper/6AJ4FLEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.13350&json=true","fetch_graph":"https://pith.science/api/pith-number/6AJ4FLEXKM6ZSGOOWCX3DBBBXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6AJ4FLEXKM6ZSGOOWCX3DBBBXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6AJ4FLEXKM6ZSGOOWCX3DBBBXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6AJ4FLEXKM6ZSGOOWCX3DBBBXJ/action/storage_attestation","attest_author":"https://pith.science/pith/6AJ4FLEXKM6ZSGOOWCX3DBBBXJ/action/author_attestation","sign_citation":"https://pith.science/pith/6AJ4FLEXKM6ZSGOOWCX3DBBBXJ/action/citation_signature","submit_replication":"https://pith.science/pith/6AJ4FLEXKM6ZSGOOWCX3DBBBXJ/action/replication_record"}},"created_at":"2026-07-05T00:51:22.332382+00:00","updated_at":"2026-07-05T00:51:22.332382+00:00"}