{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:E6DUKVILVZ2ZJ5AVKT5QXTZ4Y5","short_pith_number":"pith:E6DUKVIL","schema_version":"1.0","canonical_sha256":"278745550bae7594f41554fb0bcf3cc77971174e14688c67125f95a1cb0f6a4a","source":{"kind":"arxiv","id":"2012.06031","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning Agents for Ubisoft's Roller Champions","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aurelien Simoni, Eloi Alonso, Maxim Peter, Nancy Iskander","submitted_at":"2020-12-10T23:53:15Z","abstract_excerpt":"In recent years, Reinforcement Learning (RL) has seen increasing popularity in research and popular culture. However, skepticism still surrounds the practicality of RL in modern video game development. In this paper, we demonstrate by example that RL can be a great tool for Artificial Intelligence (AI) design in modern, non-trivial video games. We present our RL system for Ubisoft's Roller Champions, a 3v3 Competitive Multiplayer Sports Game played on an oval-shaped skating arena. Our system is designed to keep up with agile, fast-paced development, taking 1--4 days to train a new model follow"},"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":"2012.06031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-10T23:53:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af62c72cef93aed6bc801a92521ca27050ade8ab2d0648d753540d5a82fc27e9","abstract_canon_sha256":"abdea62cfe292b0430bb47845521af9ea68d0c7fb53447631a1d97c8743cf5ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:46.710709Z","signature_b64":"a8IGXtema3HI8VPXw0wqVhHxTEb9/P28pV4+iRDNU/n8OM0IxZpbYSm5hb9hoq1CcJyxVhYpSQFBSGehgDq+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"278745550bae7594f41554fb0bcf3cc77971174e14688c67125f95a1cb0f6a4a","last_reissued_at":"2026-07-05T01:58:46.710227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:46.710227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning Agents for Ubisoft's Roller Champions","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aurelien Simoni, Eloi Alonso, Maxim Peter, Nancy Iskander","submitted_at":"2020-12-10T23:53:15Z","abstract_excerpt":"In recent years, Reinforcement Learning (RL) has seen increasing popularity in research and popular culture. However, skepticism still surrounds the practicality of RL in modern video game development. In this paper, we demonstrate by example that RL can be a great tool for Artificial Intelligence (AI) design in modern, non-trivial video games. We present our RL system for Ubisoft's Roller Champions, a 3v3 Competitive Multiplayer Sports Game played on an oval-shaped skating arena. Our system is designed to keep up with agile, fast-paced development, taking 1--4 days to train a new model follow"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.06031","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/2012.06031/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":"2012.06031","created_at":"2026-07-05T01:58:46.710281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.06031v1","created_at":"2026-07-05T01:58:46.710281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.06031","created_at":"2026-07-05T01:58:46.710281+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6DUKVILVZ2Z","created_at":"2026-07-05T01:58:46.710281+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6DUKVILVZ2ZJ5AV","created_at":"2026-07-05T01:58:46.710281+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6DUKVIL","created_at":"2026-07-05T01:58:46.710281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03682","citing_title":"A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E6DUKVILVZ2ZJ5AVKT5QXTZ4Y5","json":"https://pith.science/pith/E6DUKVILVZ2ZJ5AVKT5QXTZ4Y5.json","graph_json":"https://pith.science/api/pith-number/E6DUKVILVZ2ZJ5AVKT5QXTZ4Y5/graph.json","events_json":"https://pith.science/api/pith-number/E6DUKVILVZ2ZJ5AVKT5QXTZ4Y5/events.json","paper":"https://pith.science/paper/E6DUKVIL"},"agent_actions":{"view_html":"https://pith.science/pith/E6DUKVILVZ2ZJ5AVKT5QXTZ4Y5","download_json":"https://pith.science/pith/E6DUKVILVZ2ZJ5AVKT5QXTZ4Y5.json","view_paper":"https://pith.science/paper/E6DUKVIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.06031&json=true","fetch_graph":"https://pith.science/api/pith-number/E6DUKVILVZ2ZJ5AVKT5QXTZ4Y5/graph.json","fetch_events":"https://pith.science/api/pith-number/E6DUKVILVZ2ZJ5AVKT5QXTZ4Y5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6DUKVILVZ2ZJ5AVKT5QXTZ4Y5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6DUKVILVZ2ZJ5AVKT5QXTZ4Y5/action/storage_attestation","attest_author":"https://pith.science/pith/E6DUKVILVZ2ZJ5AVKT5QXTZ4Y5/action/author_attestation","sign_citation":"https://pith.science/pith/E6DUKVILVZ2ZJ5AVKT5QXTZ4Y5/action/citation_signature","submit_replication":"https://pith.science/pith/E6DUKVILVZ2ZJ5AVKT5QXTZ4Y5/action/replication_record"}},"created_at":"2026-07-05T01:58:46.710281+00:00","updated_at":"2026-07-05T01:58:46.710281+00:00"}