{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YKFMNSXKVEACS4IXBXS4IV3IOA","short_pith_number":"pith:YKFMNSXK","schema_version":"1.0","canonical_sha256":"c28ac6caeaa9002971170de5c45768702dc99f4aceab60e13976ed5fd55f8420","source":{"kind":"arxiv","id":"2004.13291","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Rainbow DQN Agent in Hanabi with Unseen Partners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Andy Nealen, Julian Togelius, Rodrigo Canaan, Stefan Menzel, Xianbo Gao, Youjin Chung","submitted_at":"2020-04-28T04:24:44Z","abstract_excerpt":"Hanabi is a cooperative game that challenges exist-ing AI techniques due to its focus on modeling the mental states ofother players to interpret and predict their behavior. While thereare agents that can achieve near-perfect scores in the game byagreeing on some shared strategy, comparatively little progresshas been made in ad-hoc cooperation settings, where partnersand strategies are not known in advance. In this paper, we showthat agents trained through self-play using the popular RainbowDQN architecture fail to cooperate well with simple rule-basedagents that were not seen during training a"},"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":"2004.13291","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-28T04:24:44Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"7e4ea0ff55937a3e36bacee4e4d7f77b0e505f5aa2d425affc7937d73ccb9bbf","abstract_canon_sha256":"9977192745bada0223a310bd68744eb98f13877a36c9af755902718f5f5a62da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:57.638766Z","signature_b64":"m2T6TGz2EoLbdECQFG69gSL9bLNd0P+y3vSqACzXCNLRgSRqPS1EPv19xBziOc8aJGtUt51HOSufgMU6hn52Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c28ac6caeaa9002971170de5c45768702dc99f4aceab60e13976ed5fd55f8420","last_reissued_at":"2026-07-05T00:58:57.638263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:57.638263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Rainbow DQN Agent in Hanabi with Unseen Partners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Andy Nealen, Julian Togelius, Rodrigo Canaan, Stefan Menzel, Xianbo Gao, Youjin Chung","submitted_at":"2020-04-28T04:24:44Z","abstract_excerpt":"Hanabi is a cooperative game that challenges exist-ing AI techniques due to its focus on modeling the mental states ofother players to interpret and predict their behavior. While thereare agents that can achieve near-perfect scores in the game byagreeing on some shared strategy, comparatively little progresshas been made in ad-hoc cooperation settings, where partnersand strategies are not known in advance. In this paper, we showthat agents trained through self-play using the popular RainbowDQN architecture fail to cooperate well with simple rule-basedagents that were not seen during training a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13291","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/2004.13291/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":"2004.13291","created_at":"2026-07-05T00:58:57.638333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.13291v1","created_at":"2026-07-05T00:58:57.638333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13291","created_at":"2026-07-05T00:58:57.638333+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKFMNSXKVEAC","created_at":"2026-07-05T00:58:57.638333+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKFMNSXKVEACS4IX","created_at":"2026-07-05T00:58:57.638333+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKFMNSXK","created_at":"2026-07-05T00:58:57.638333+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06116","citing_title":"Event Vision Sensor: A Review","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKFMNSXKVEACS4IXBXS4IV3IOA","json":"https://pith.science/pith/YKFMNSXKVEACS4IXBXS4IV3IOA.json","graph_json":"https://pith.science/api/pith-number/YKFMNSXKVEACS4IXBXS4IV3IOA/graph.json","events_json":"https://pith.science/api/pith-number/YKFMNSXKVEACS4IXBXS4IV3IOA/events.json","paper":"https://pith.science/paper/YKFMNSXK"},"agent_actions":{"view_html":"https://pith.science/pith/YKFMNSXKVEACS4IXBXS4IV3IOA","download_json":"https://pith.science/pith/YKFMNSXKVEACS4IXBXS4IV3IOA.json","view_paper":"https://pith.science/paper/YKFMNSXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.13291&json=true","fetch_graph":"https://pith.science/api/pith-number/YKFMNSXKVEACS4IXBXS4IV3IOA/graph.json","fetch_events":"https://pith.science/api/pith-number/YKFMNSXKVEACS4IXBXS4IV3IOA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKFMNSXKVEACS4IXBXS4IV3IOA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKFMNSXKVEACS4IXBXS4IV3IOA/action/storage_attestation","attest_author":"https://pith.science/pith/YKFMNSXKVEACS4IXBXS4IV3IOA/action/author_attestation","sign_citation":"https://pith.science/pith/YKFMNSXKVEACS4IXBXS4IV3IOA/action/citation_signature","submit_replication":"https://pith.science/pith/YKFMNSXKVEACS4IXBXS4IV3IOA/action/replication_record"}},"created_at":"2026-07-05T00:58:57.638333+00:00","updated_at":"2026-07-05T00:58:57.638333+00:00"}