{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7RAXB4LP3Y54KPAAEB6R2WIZ3W","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":"53c5da4bb5945cdda1a336765b8186c132d6e3934e0b6f42361642f3662ab291","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-19T12:01:41Z","title_canon_sha256":"43209f5111ae189424c4e79cd645e36c754c748492017472d336a6b5320e01ad"},"schema_version":"1.0","source":{"id":"2301.08028","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.08028","created_at":"2026-07-05T11:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"2301.08028v4","created_at":"2026-07-05T11:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08028","created_at":"2026-07-05T11:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"7RAXB4LP3Y54","created_at":"2026-07-05T11:11:29Z"},{"alias_kind":"pith_short_16","alias_value":"7RAXB4LP3Y54KPAA","created_at":"2026-07-05T11:11:29Z"},{"alias_kind":"pith_short_8","alias_value":"7RAXB4LP","created_at":"2026-07-05T11:11:29Z"}],"graph_snapshots":[{"event_id":"sha256:8f01b2e274744db1eb4aee0277ccc578af3798c741b3503b782291a722907d29","target":"graph","created_at":"2026-07-05T11:11:29Z","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/2301.08028/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While deep reinforcement learning (RL) has fueled multiple high-profile successes in machine learning, it is held back from more widespread adoption by its often poor data efficiency and the limited generality of the policies it produces. A promising approach for alleviating these limitations is to cast the development of better RL algorithms as a machine learning problem itself in a process called meta-RL. Meta-RL is most commonly studied in a problem setting where, given a distribution of tasks, the goal is to learn a policy that is capable of adapting to any new task from the task distribut","authors_text":"Chelsea Finn, Evan Zheran Liu, Jacob Beck, Luisa Zintgraf, Risto Vuorio, Shimon Whiteson, Zheng Xiong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-19T12:01:41Z","title":"A Tutorial on Meta-Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08028","kind":"arxiv","version":4},"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:b49741715d72cfc8a1aa26e7114dd9a961725e2c532b78532d4b07777a9de8c0","target":"record","created_at":"2026-07-05T11:11:29Z","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":"53c5da4bb5945cdda1a336765b8186c132d6e3934e0b6f42361642f3662ab291","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-19T12:01:41Z","title_canon_sha256":"43209f5111ae189424c4e79cd645e36c754c748492017472d336a6b5320e01ad"},"schema_version":"1.0","source":{"id":"2301.08028","kind":"arxiv","version":4}},"canonical_sha256":"fc4170f16fde3bc53c00207d1d5919ddb7b54cf1ec585c3d7d4fe02ff2ef878f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc4170f16fde3bc53c00207d1d5919ddb7b54cf1ec585c3d7d4fe02ff2ef878f","first_computed_at":"2026-07-05T11:11:29.338357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:29.338357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1+h1WaR2ALccQM/COmVc1s/zKYTsYeixDLyX5nS8cNWZs+UolwdDNVFIKgbeuwgEuX/wvkt2qYhE6FRiQPGMCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:29.339030Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.08028","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b49741715d72cfc8a1aa26e7114dd9a961725e2c532b78532d4b07777a9de8c0","sha256:8f01b2e274744db1eb4aee0277ccc578af3798c741b3503b782291a722907d29"],"state_sha256":"86d22b44b92ae1e50f052723c9dcb693e41b140fac3aaae67821f08a68aed9ab"}