{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TLAWSX45AURJ4POZPOYYL5IWIZ","short_pith_number":"pith:TLAWSX45","schema_version":"1.0","canonical_sha256":"9ac1695f9d05229e3dd97bb185f5164659b3c98f9cc968618c7a65be1eb0bd95","source":{"kind":"arxiv","id":"2204.11828","version":1},"attestation_state":"computed","paper":{"title":"Skill-based Meta-Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Joseph J Lim, Karl Pertsch, Shao-Hua Sun, Sung Ju Hwang, Taewook Nam","submitted_at":"2022-04-25T17:58:19Z","abstract_excerpt":"While deep reinforcement learning methods have shown impressive results in robot learning, their sample inefficiency makes the learning of complex, long-horizon behaviors with real robot systems infeasible. To mitigate this issue, meta-reinforcement learning methods aim to enable fast learning on novel tasks by learning how to learn. Yet, the application has been limited to short-horizon tasks with dense rewards. To enable learning long-horizon behaviors, recent works have explored leveraging prior experience in the form of offline datasets without reward or task annotations. While these appro"},"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":"2204.11828","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-25T17:58:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af9eba27b79825fac4cad342e205b8afeadcde503c155cdf8a26e5236acf57a3","abstract_canon_sha256":"2e28f7511303c79570a7e6320e8338e1939bccbedd254646e63b3819768ba6be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:31.998842Z","signature_b64":"6hK9XFdn/xl/rml9dvDvpDIyalWz3ak5ioH+1Nd9ZvBxCM9qGoA5zEpRAqaNEB+bJKoNnpmWzSvX5sRCXApnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ac1695f9d05229e3dd97bb185f5164659b3c98f9cc968618c7a65be1eb0bd95","last_reissued_at":"2026-07-05T04:17:31.998368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:31.998368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skill-based Meta-Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Joseph J Lim, Karl Pertsch, Shao-Hua Sun, Sung Ju Hwang, Taewook Nam","submitted_at":"2022-04-25T17:58:19Z","abstract_excerpt":"While deep reinforcement learning methods have shown impressive results in robot learning, their sample inefficiency makes the learning of complex, long-horizon behaviors with real robot systems infeasible. To mitigate this issue, meta-reinforcement learning methods aim to enable fast learning on novel tasks by learning how to learn. Yet, the application has been limited to short-horizon tasks with dense rewards. To enable learning long-horizon behaviors, recent works have explored leveraging prior experience in the form of offline datasets without reward or task annotations. While these appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11828","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/2204.11828/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":"2204.11828","created_at":"2026-07-05T04:17:31.998426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.11828v1","created_at":"2026-07-05T04:17:31.998426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11828","created_at":"2026-07-05T04:17:31.998426+00:00"},{"alias_kind":"pith_short_12","alias_value":"TLAWSX45AURJ","created_at":"2026-07-05T04:17:31.998426+00:00"},{"alias_kind":"pith_short_16","alias_value":"TLAWSX45AURJ4POZ","created_at":"2026-07-05T04:17:31.998426+00:00"},{"alias_kind":"pith_short_8","alias_value":"TLAWSX45","created_at":"2026-07-05T04:17:31.998426+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02834","citing_title":"Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TLAWSX45AURJ4POZPOYYL5IWIZ","json":"https://pith.science/pith/TLAWSX45AURJ4POZPOYYL5IWIZ.json","graph_json":"https://pith.science/api/pith-number/TLAWSX45AURJ4POZPOYYL5IWIZ/graph.json","events_json":"https://pith.science/api/pith-number/TLAWSX45AURJ4POZPOYYL5IWIZ/events.json","paper":"https://pith.science/paper/TLAWSX45"},"agent_actions":{"view_html":"https://pith.science/pith/TLAWSX45AURJ4POZPOYYL5IWIZ","download_json":"https://pith.science/pith/TLAWSX45AURJ4POZPOYYL5IWIZ.json","view_paper":"https://pith.science/paper/TLAWSX45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.11828&json=true","fetch_graph":"https://pith.science/api/pith-number/TLAWSX45AURJ4POZPOYYL5IWIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TLAWSX45AURJ4POZPOYYL5IWIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TLAWSX45AURJ4POZPOYYL5IWIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TLAWSX45AURJ4POZPOYYL5IWIZ/action/storage_attestation","attest_author":"https://pith.science/pith/TLAWSX45AURJ4POZPOYYL5IWIZ/action/author_attestation","sign_citation":"https://pith.science/pith/TLAWSX45AURJ4POZPOYYL5IWIZ/action/citation_signature","submit_replication":"https://pith.science/pith/TLAWSX45AURJ4POZPOYYL5IWIZ/action/replication_record"}},"created_at":"2026-07-05T04:17:31.998426+00:00","updated_at":"2026-07-05T04:17:31.998426+00:00"}