{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4NUTDUGBTNX2ZJAZO37Y6FY7ZT","short_pith_number":"pith:4NUTDUGB","schema_version":"1.0","canonical_sha256":"e36931d0c19b6faca41976ff8f171fccfab93a390c6aac75df5da42312c36c68","source":{"kind":"arxiv","id":"2012.13490","version":2},"attestation_state":"computed","paper":{"title":"Towards Continual Reinforcement Learning: A Review and Perspectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Irina Rish, Khimya Khetarpal, Matthew Riemer","submitted_at":"2020-12-25T02:35:27Z","abstract_excerpt":"In this article, we aim to provide a literature review of different formulations and approaches to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We begin by discussing our perspective on why RL is a natural fit for studying continual learning. We then provide a taxonomy of different continual RL formulations by mathematically characterizing two key properties of non-stationarity, namely, the scope and driver non-stationarity. This offers a unified view of various formulations. Next, we review and present a taxonomy of continual RL approaches. We go on to d"},"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":"2012.13490","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-25T02:35:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a47580932b3ec710190d4c0346ed54b04fd1d1ebc2d59d59edf2f3b8b9757c8e","abstract_canon_sha256":"c99f7e054037eabfb85c0974a76d85fe008d40e58e5e6a2fab9582fb19452c7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:21.530960Z","signature_b64":"rqycqPR0dxVSqpLI01GBgNMxtDwApS1o2oKj6HPdrNi/GUR4wd8o4DXqUy3NS3enQDFZMENvzWmzCAEUC/LbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e36931d0c19b6faca41976ff8f171fccfab93a390c6aac75df5da42312c36c68","last_reissued_at":"2026-07-05T05:15:21.530497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:21.530497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Continual Reinforcement Learning: A Review and Perspectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Irina Rish, Khimya Khetarpal, Matthew Riemer","submitted_at":"2020-12-25T02:35:27Z","abstract_excerpt":"In this article, we aim to provide a literature review of different formulations and approaches to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We begin by discussing our perspective on why RL is a natural fit for studying continual learning. We then provide a taxonomy of different continual RL formulations by mathematically characterizing two key properties of non-stationarity, namely, the scope and driver non-stationarity. This offers a unified view of various formulations. Next, we review and present a taxonomy of continual RL approaches. We go on to d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.13490","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/2012.13490/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":"2012.13490","created_at":"2026-07-05T05:15:21.530551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.13490v2","created_at":"2026-07-05T05:15:21.530551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.13490","created_at":"2026-07-05T05:15:21.530551+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NUTDUGBTNX2","created_at":"2026-07-05T05:15:21.530551+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NUTDUGBTNX2ZJAZ","created_at":"2026-07-05T05:15:21.530551+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NUTDUGB","created_at":"2026-07-05T05:15:21.530551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23565","citing_title":"Understanding Goal Generalisation in Sequential Reinforcement Learning","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4NUTDUGBTNX2ZJAZO37Y6FY7ZT","json":"https://pith.science/pith/4NUTDUGBTNX2ZJAZO37Y6FY7ZT.json","graph_json":"https://pith.science/api/pith-number/4NUTDUGBTNX2ZJAZO37Y6FY7ZT/graph.json","events_json":"https://pith.science/api/pith-number/4NUTDUGBTNX2ZJAZO37Y6FY7ZT/events.json","paper":"https://pith.science/paper/4NUTDUGB"},"agent_actions":{"view_html":"https://pith.science/pith/4NUTDUGBTNX2ZJAZO37Y6FY7ZT","download_json":"https://pith.science/pith/4NUTDUGBTNX2ZJAZO37Y6FY7ZT.json","view_paper":"https://pith.science/paper/4NUTDUGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.13490&json=true","fetch_graph":"https://pith.science/api/pith-number/4NUTDUGBTNX2ZJAZO37Y6FY7ZT/graph.json","fetch_events":"https://pith.science/api/pith-number/4NUTDUGBTNX2ZJAZO37Y6FY7ZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NUTDUGBTNX2ZJAZO37Y6FY7ZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NUTDUGBTNX2ZJAZO37Y6FY7ZT/action/storage_attestation","attest_author":"https://pith.science/pith/4NUTDUGBTNX2ZJAZO37Y6FY7ZT/action/author_attestation","sign_citation":"https://pith.science/pith/4NUTDUGBTNX2ZJAZO37Y6FY7ZT/action/citation_signature","submit_replication":"https://pith.science/pith/4NUTDUGBTNX2ZJAZO37Y6FY7ZT/action/replication_record"}},"created_at":"2026-07-05T05:15:21.530551+00:00","updated_at":"2026-07-05T05:15:21.530551+00:00"}