{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:72VV5WV37KMFIK4STJR4VOHMAE","short_pith_number":"pith:72VV5WV3","schema_version":"1.0","canonical_sha256":"feab5edabbfa98542b929a63cab8ec0138256756fe30dd38bdaabf7bb53d8d3e","source":{"kind":"arxiv","id":"2011.14826","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Johan S. Obando-Ceron, Pablo Samuel Castro","submitted_at":"2020-11-20T15:23:40Z","abstract_excerpt":"Since the introduction of DQN, a vast majority of reinforcement learning research has focused on reinforcement learning with deep neural networks as function approximators. New methods are typically evaluated on a set of environments that have now become standard, such as Atari 2600 games. While these benchmarks help standardize evaluation, their computational cost has the unfortunate side effect of widening the gap between those with ample access to computational resources, and those without. In this work we argue that, despite the community's emphasis on large-scale environments, the traditi"},"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":"2011.14826","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-20T15:23:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be0715383ac6fc5a1818ae6145870650d8b4d800f0e160fe982fa9ee1909667c","abstract_canon_sha256":"424072524135cf021439ecbd2fbe87fb3049fb0d5c17727e15fd5328d8103a72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:13.603405Z","signature_b64":"OKOQFB7ZnMgNn03rJuKO0gqowaGWmcsWwai/gNYEXEEbDMSdyHGQjslKn7mPKeu3zIlnxait2KcirElde+lGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"feab5edabbfa98542b929a63cab8ec0138256756fe30dd38bdaabf7bb53d8d3e","last_reissued_at":"2026-07-05T02:42:13.603028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:13.603028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Johan S. Obando-Ceron, Pablo Samuel Castro","submitted_at":"2020-11-20T15:23:40Z","abstract_excerpt":"Since the introduction of DQN, a vast majority of reinforcement learning research has focused on reinforcement learning with deep neural networks as function approximators. New methods are typically evaluated on a set of environments that have now become standard, such as Atari 2600 games. While these benchmarks help standardize evaluation, their computational cost has the unfortunate side effect of widening the gap between those with ample access to computational resources, and those without. In this work we argue that, despite the community's emphasis on large-scale environments, the traditi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14826","kind":"arxiv","version":2},"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/2011.14826/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":"2011.14826","created_at":"2026-07-05T02:42:13.603088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.14826v2","created_at":"2026-07-05T02:42:13.603088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14826","created_at":"2026-07-05T02:42:13.603088+00:00"},{"alias_kind":"pith_short_12","alias_value":"72VV5WV37KMF","created_at":"2026-07-05T02:42:13.603088+00:00"},{"alias_kind":"pith_short_16","alias_value":"72VV5WV37KMFIK4S","created_at":"2026-07-05T02:42:13.603088+00:00"},{"alias_kind":"pith_short_8","alias_value":"72VV5WV3","created_at":"2026-07-05T02:42:13.603088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05716","citing_title":"Ensemble Elastic DQN: A Step Dependent Ensemble Approach for Reducing Overestimation in Deep Value-Based Reinforcement Learning","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/72VV5WV37KMFIK4STJR4VOHMAE","json":"https://pith.science/pith/72VV5WV37KMFIK4STJR4VOHMAE.json","graph_json":"https://pith.science/api/pith-number/72VV5WV37KMFIK4STJR4VOHMAE/graph.json","events_json":"https://pith.science/api/pith-number/72VV5WV37KMFIK4STJR4VOHMAE/events.json","paper":"https://pith.science/paper/72VV5WV3"},"agent_actions":{"view_html":"https://pith.science/pith/72VV5WV37KMFIK4STJR4VOHMAE","download_json":"https://pith.science/pith/72VV5WV37KMFIK4STJR4VOHMAE.json","view_paper":"https://pith.science/paper/72VV5WV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.14826&json=true","fetch_graph":"https://pith.science/api/pith-number/72VV5WV37KMFIK4STJR4VOHMAE/graph.json","fetch_events":"https://pith.science/api/pith-number/72VV5WV37KMFIK4STJR4VOHMAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72VV5WV37KMFIK4STJR4VOHMAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72VV5WV37KMFIK4STJR4VOHMAE/action/storage_attestation","attest_author":"https://pith.science/pith/72VV5WV37KMFIK4STJR4VOHMAE/action/author_attestation","sign_citation":"https://pith.science/pith/72VV5WV37KMFIK4STJR4VOHMAE/action/citation_signature","submit_replication":"https://pith.science/pith/72VV5WV37KMFIK4STJR4VOHMAE/action/replication_record"}},"created_at":"2026-07-05T02:42:13.603088+00:00","updated_at":"2026-07-05T02:42:13.603088+00:00"}