{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6ERMVMRE32FHFANQWCSCNSXNXT","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":"2b6cc6f53797dc65a0cb52404289685f5aa6b163ef1f4f67a43ad462cbebadff","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-30T21:50:32Z","title_canon_sha256":"fcd8ff33420ad611a76257ce4a536d286229d82c53f06aa2bb8b8cef2f32eb9a"},"schema_version":"1.0","source":{"id":"1910.00125","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.00125","created_at":"2026-07-05T00:52:36Z"},{"alias_kind":"arxiv_version","alias_value":"1910.00125v2","created_at":"2026-07-05T00:52:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.00125","created_at":"2026-07-05T00:52:36Z"},{"alias_kind":"pith_short_12","alias_value":"6ERMVMRE32FH","created_at":"2026-07-05T00:52:36Z"},{"alias_kind":"pith_short_16","alias_value":"6ERMVMRE32FHFANQ","created_at":"2026-07-05T00:52:36Z"},{"alias_kind":"pith_short_8","alias_value":"6ERMVMRE","created_at":"2026-07-05T00:52:36Z"}],"graph_snapshots":[{"event_id":"sha256:2e928b3934267d1f3f235a138aaa566b10508d43d03cf430343d391229cf9d95","target":"graph","created_at":"2026-07-05T00:52:36Z","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/1910.00125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. First, we show that Q-learning is competitive with state-of-the-art meta-RL algorithms if given access to a context variable that is a representation of the past trajectory. Second, a multi-task objective to maximize the average reward across the training tasks is an effective method to meta-train RL policies. Third, past data from the meta-training replay buffer can be recycled to adapt the policy on a new task using off-policy updates. MQL dra","authors_text":"Alexander J. Smola, Pratik Chaudhari, Rasool Fakoor, Stefano Soatto","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-30T21:50:32Z","title":"Meta-Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.00125","kind":"arxiv","version":2},"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:c8673d57e0fa50a2bd6d8700c88e4f4de612663dd1a377920c562b827a9aa9d7","target":"record","created_at":"2026-07-05T00:52:36Z","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":"2b6cc6f53797dc65a0cb52404289685f5aa6b163ef1f4f67a43ad462cbebadff","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-30T21:50:32Z","title_canon_sha256":"fcd8ff33420ad611a76257ce4a536d286229d82c53f06aa2bb8b8cef2f32eb9a"},"schema_version":"1.0","source":{"id":"1910.00125","kind":"arxiv","version":2}},"canonical_sha256":"f122cab224de8a7281b0b0a426caedbccdb67544369e75a577a39aaa33372f02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f122cab224de8a7281b0b0a426caedbccdb67544369e75a577a39aaa33372f02","first_computed_at":"2026-07-05T00:52:36.418302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:52:36.418302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OoVmsr+QzbEs3OvmTGZnikrnhoMQXMx8bgAYe8uvWYJ7WtAaxHbBJtQWF7hLA6z4dTVvaarPWW+oARB9NJubAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:52:36.418733Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.00125","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8673d57e0fa50a2bd6d8700c88e4f4de612663dd1a377920c562b827a9aa9d7","sha256:2e928b3934267d1f3f235a138aaa566b10508d43d03cf430343d391229cf9d95"],"state_sha256":"2bb2a558a132b3b5f3b65ec05e74a530355ef9677ed2f8441a459e3e825b5d75"}