{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TLAWSX45AURJ4POZPOYYL5IWIZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2e28f7511303c79570a7e6320e8338e1939bccbedd254646e63b3819768ba6be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-25T17:58:19Z","title_canon_sha256":"af9eba27b79825fac4cad342e205b8afeadcde503c155cdf8a26e5236acf57a3"},"schema_version":"1.0","source":{"id":"2204.11828","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.11828","created_at":"2026-07-05T04:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"2204.11828v1","created_at":"2026-07-05T04:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11828","created_at":"2026-07-05T04:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"TLAWSX45AURJ","created_at":"2026-07-05T04:17:31Z"},{"alias_kind":"pith_short_16","alias_value":"TLAWSX45AURJ4POZ","created_at":"2026-07-05T04:17:31Z"},{"alias_kind":"pith_short_8","alias_value":"TLAWSX45","created_at":"2026-07-05T04:17:31Z"}],"graph_snapshots":[{"event_id":"sha256:04155ecbe4d7bfad7485fa60aeaf2aa3e784d4cfb80e61f45e6e94914e961526","target":"graph","created_at":"2026-07-05T04:17:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2204.11828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Joseph J Lim, Karl Pertsch, Shao-Hua Sun, Sung Ju Hwang, Taewook Nam","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-25T17:58:19Z","title":"Skill-based Meta-Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11828","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4c4d2dcec7372095dbfaebc39e4b01a83f76eb3fa89ea8546a0dd67fa8223d68","target":"record","created_at":"2026-07-05T04:17:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2e28f7511303c79570a7e6320e8338e1939bccbedd254646e63b3819768ba6be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-25T17:58:19Z","title_canon_sha256":"af9eba27b79825fac4cad342e205b8afeadcde503c155cdf8a26e5236acf57a3"},"schema_version":"1.0","source":{"id":"2204.11828","kind":"arxiv","version":1}},"canonical_sha256":"9ac1695f9d05229e3dd97bb185f5164659b3c98f9cc968618c7a65be1eb0bd95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ac1695f9d05229e3dd97bb185f5164659b3c98f9cc968618c7a65be1eb0bd95","first_computed_at":"2026-07-05T04:17:31.998368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:31.998368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6hK9XFdn/xl/rml9dvDvpDIyalWz3ak5ioH+1Nd9ZvBxCM9qGoA5zEpRAqaNEB+bJKoNnpmWzSvX5sRCXApnCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:31.998842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.11828","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c4d2dcec7372095dbfaebc39e4b01a83f76eb3fa89ea8546a0dd67fa8223d68","sha256:04155ecbe4d7bfad7485fa60aeaf2aa3e784d4cfb80e61f45e6e94914e961526"],"state_sha256":"0d8156353b8809a0584936faaca3012d00904bfdd44eb8dcc1f8d197e83b8f6c"}