{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IZD3VIAOXD6QIPOLUMWNKB2N2L","short_pith_number":"pith:IZD3VIAO","schema_version":"1.0","canonical_sha256":"4647baa00eb8fd043dcba32cd5074dd2d02d927900bd5261e66f602204372b79","source":{"kind":"arxiv","id":"2112.04467","version":1},"attestation_state":"computed","paper":{"title":"CoMPS: Continual Meta Policy Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Glen Berseth, Grace Zhang, Sergey Levine, Zhiwei Zhang","submitted_at":"2021-12-08T18:53:08Z","abstract_excerpt":"We develop a new continual meta-learning method to address challenges in sequential multi-task learning. In this setting, the agent's goal is to achieve high reward over any sequence of tasks quickly. Prior meta-reinforcement learning algorithms have demonstrated promising results in accelerating the acquisition of new tasks. However, they require access to all tasks during training. Beyond simply transferring past experience to new tasks, our goal is to devise continual reinforcement learning algorithms that learn to learn, using their experience on previous tasks to learn new tasks more quic"},"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":"2112.04467","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-08T18:53:08Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"bddefc26d3b9e40e8d4288887839f7bf409875f2dc8f1beaf8b37b8a49126968","abstract_canon_sha256":"d71c2b6b83423e04694060f859d386f22ab38e15297c0ad2ec9a8452e8a54200"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:09.795650Z","signature_b64":"SzJRInxYXrbg4fHKx03frK/fOOyIxclUZy3LHaUHLt0m2hSHd6aWAibFuYohrr2R6P8F/ab+Ies2q6iEF9BcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4647baa00eb8fd043dcba32cd5074dd2d02d927900bd5261e66f602204372b79","last_reissued_at":"2026-07-05T03:39:09.795261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:09.795261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoMPS: Continual Meta Policy Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Glen Berseth, Grace Zhang, Sergey Levine, Zhiwei Zhang","submitted_at":"2021-12-08T18:53:08Z","abstract_excerpt":"We develop a new continual meta-learning method to address challenges in sequential multi-task learning. In this setting, the agent's goal is to achieve high reward over any sequence of tasks quickly. Prior meta-reinforcement learning algorithms have demonstrated promising results in accelerating the acquisition of new tasks. However, they require access to all tasks during training. Beyond simply transferring past experience to new tasks, our goal is to devise continual reinforcement learning algorithms that learn to learn, using their experience on previous tasks to learn new tasks more quic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04467","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/2112.04467/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":"2112.04467","created_at":"2026-07-05T03:39:09.795323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.04467v1","created_at":"2026-07-05T03:39:09.795323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04467","created_at":"2026-07-05T03:39:09.795323+00:00"},{"alias_kind":"pith_short_12","alias_value":"IZD3VIAOXD6Q","created_at":"2026-07-05T03:39:09.795323+00:00"},{"alias_kind":"pith_short_16","alias_value":"IZD3VIAOXD6QIPOL","created_at":"2026-07-05T03:39:09.795323+00:00"},{"alias_kind":"pith_short_8","alias_value":"IZD3VIAO","created_at":"2026-07-05T03:39:09.795323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.08827","citing_title":"A Survey of Reinforcement Learning for Large Reasoning Models","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IZD3VIAOXD6QIPOLUMWNKB2N2L","json":"https://pith.science/pith/IZD3VIAOXD6QIPOLUMWNKB2N2L.json","graph_json":"https://pith.science/api/pith-number/IZD3VIAOXD6QIPOLUMWNKB2N2L/graph.json","events_json":"https://pith.science/api/pith-number/IZD3VIAOXD6QIPOLUMWNKB2N2L/events.json","paper":"https://pith.science/paper/IZD3VIAO"},"agent_actions":{"view_html":"https://pith.science/pith/IZD3VIAOXD6QIPOLUMWNKB2N2L","download_json":"https://pith.science/pith/IZD3VIAOXD6QIPOLUMWNKB2N2L.json","view_paper":"https://pith.science/paper/IZD3VIAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.04467&json=true","fetch_graph":"https://pith.science/api/pith-number/IZD3VIAOXD6QIPOLUMWNKB2N2L/graph.json","fetch_events":"https://pith.science/api/pith-number/IZD3VIAOXD6QIPOLUMWNKB2N2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IZD3VIAOXD6QIPOLUMWNKB2N2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IZD3VIAOXD6QIPOLUMWNKB2N2L/action/storage_attestation","attest_author":"https://pith.science/pith/IZD3VIAOXD6QIPOLUMWNKB2N2L/action/author_attestation","sign_citation":"https://pith.science/pith/IZD3VIAOXD6QIPOLUMWNKB2N2L/action/citation_signature","submit_replication":"https://pith.science/pith/IZD3VIAOXD6QIPOLUMWNKB2N2L/action/replication_record"}},"created_at":"2026-07-05T03:39:09.795323+00:00","updated_at":"2026-07-05T03:39:09.795323+00:00"}