{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DBM6UKDDSIZSPNSGNPI3PJRVLQ","short_pith_number":"pith:DBM6UKDD","schema_version":"1.0","canonical_sha256":"1859ea2863923327b6466bd1b7a6355c3807e64402c6f401ad82bb3b4246e2d5","source":{"kind":"arxiv","id":"2103.03216","version":2},"attestation_state":"computed","paper":{"title":"Continuous Coordination As a Realistic Scenario for Lifelong Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Akilesh Badrinaaraayanan, Hadi Nekoei, Sarath Chandar","submitted_at":"2021-03-04T18:44:03Z","abstract_excerpt":"Current deep reinforcement learning (RL) algorithms are still highly task-specific and lack the ability to generalize to new environments. Lifelong learning (LLL), however, aims at solving multiple tasks sequentially by efficiently transferring and using knowledge between tasks. Despite a surge of interest in lifelong RL in recent years, the lack of a realistic testbed makes robust evaluation of LLL algorithms difficult. Multi-agent RL (MARL), on the other hand, can be seen as a natural scenario for lifelong RL due to its inherent non-stationarity, since the agents' policies change over time. "},"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":"2103.03216","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T18:44:03Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"4178accc4d94ced528b16598b8b1891602b2469e1129fcc516519aacc00281d4","abstract_canon_sha256":"cb11cf8eca16f22f9b948fdf1e049a73bf40813e9d3e685376dde525e4b42d1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:59.885164Z","signature_b64":"8FroBvwaE8esZXR1nT595V7pgB5cWOjxfn1swyjMMlRhBQM+F884zzlRbG8M2SsRsYT39v3yfTPhOyhnStAGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1859ea2863923327b6466bd1b7a6355c3807e64402c6f401ad82bb3b4246e2d5","last_reissued_at":"2026-07-05T02:48:59.884696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:59.884696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuous Coordination As a Realistic Scenario for Lifelong Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Akilesh Badrinaaraayanan, Hadi Nekoei, Sarath Chandar","submitted_at":"2021-03-04T18:44:03Z","abstract_excerpt":"Current deep reinforcement learning (RL) algorithms are still highly task-specific and lack the ability to generalize to new environments. Lifelong learning (LLL), however, aims at solving multiple tasks sequentially by efficiently transferring and using knowledge between tasks. Despite a surge of interest in lifelong RL in recent years, the lack of a realistic testbed makes robust evaluation of LLL algorithms difficult. Multi-agent RL (MARL), on the other hand, can be seen as a natural scenario for lifelong RL due to its inherent non-stationarity, since the agents' policies change over time. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03216","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/2103.03216/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":"2103.03216","created_at":"2026-07-05T02:48:59.884749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.03216v2","created_at":"2026-07-05T02:48:59.884749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03216","created_at":"2026-07-05T02:48:59.884749+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBM6UKDDSIZS","created_at":"2026-07-05T02:48:59.884749+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBM6UKDDSIZSPNSG","created_at":"2026-07-05T02:48:59.884749+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBM6UKDD","created_at":"2026-07-05T02:48:59.884749+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03644","citing_title":"Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DBM6UKDDSIZSPNSGNPI3PJRVLQ","json":"https://pith.science/pith/DBM6UKDDSIZSPNSGNPI3PJRVLQ.json","graph_json":"https://pith.science/api/pith-number/DBM6UKDDSIZSPNSGNPI3PJRVLQ/graph.json","events_json":"https://pith.science/api/pith-number/DBM6UKDDSIZSPNSGNPI3PJRVLQ/events.json","paper":"https://pith.science/paper/DBM6UKDD"},"agent_actions":{"view_html":"https://pith.science/pith/DBM6UKDDSIZSPNSGNPI3PJRVLQ","download_json":"https://pith.science/pith/DBM6UKDDSIZSPNSGNPI3PJRVLQ.json","view_paper":"https://pith.science/paper/DBM6UKDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.03216&json=true","fetch_graph":"https://pith.science/api/pith-number/DBM6UKDDSIZSPNSGNPI3PJRVLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/DBM6UKDDSIZSPNSGNPI3PJRVLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBM6UKDDSIZSPNSGNPI3PJRVLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBM6UKDDSIZSPNSGNPI3PJRVLQ/action/storage_attestation","attest_author":"https://pith.science/pith/DBM6UKDDSIZSPNSGNPI3PJRVLQ/action/author_attestation","sign_citation":"https://pith.science/pith/DBM6UKDDSIZSPNSGNPI3PJRVLQ/action/citation_signature","submit_replication":"https://pith.science/pith/DBM6UKDDSIZSPNSGNPI3PJRVLQ/action/replication_record"}},"created_at":"2026-07-05T02:48:59.884749+00:00","updated_at":"2026-07-05T02:48:59.884749+00:00"}