{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AGO6S6VLJU64AB7CMXX7BVLEF2","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":"adb92dfc5245d6f67d222e7a7908641a27099b80ece2bcdbcb73cc2db0fe99df","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T11:44:59Z","title_canon_sha256":"fa0dc4365b5c488b202ba9925c1076b1fbe4f44af0baf2d28e3cae679e643887"},"schema_version":"1.0","source":{"id":"1910.08348","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.08348","created_at":"2026-07-05T00:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"1910.08348v2","created_at":"2026-07-05T00:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.08348","created_at":"2026-07-05T00:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"AGO6S6VLJU64","created_at":"2026-07-05T00:44:27Z"},{"alias_kind":"pith_short_16","alias_value":"AGO6S6VLJU64AB7C","created_at":"2026-07-05T00:44:27Z"},{"alias_kind":"pith_short_8","alias_value":"AGO6S6VL","created_at":"2026-07-05T00:44:27Z"}],"graph_snapshots":[{"event_id":"sha256:734c4a3a6131dbf5576dbca8317bc853f5188d0de088e795762ab05d26e4d10d","target":"graph","created_at":"2026-07-05T00:44:27Z","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/1910.08348/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Trading off exploration and exploitation in an unknown environment is key to maximising expected return during learning. A Bayes-optimal policy, which does so optimally, conditions its actions not only on the environment state but on the agent's uncertainty about the environment. Computing a Bayes-optimal policy is however intractable for all but the smallest tasks. In this paper, we introduce variational Bayes-Adaptive Deep RL (variBAD), a way to meta-learn to perform approximate inference in an unknown environment, and incorporate task uncertainty directly during action selection. In a grid-","authors_text":"Katja Hofmann, Kyriacos Shiarlis, Luisa Zintgraf, Maximilian Igl, Sebastian Schulze, Shimon Whiteson, Yarin Gal","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T11:44:59Z","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.08348","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":"sha256:1fb3b36492a7ab1b744e15eb21c13a8fafc85789774d486a9295d78647ef4339","target":"record","created_at":"2026-07-05T00:44:27Z","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":"adb92dfc5245d6f67d222e7a7908641a27099b80ece2bcdbcb73cc2db0fe99df","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T11:44:59Z","title_canon_sha256":"fa0dc4365b5c488b202ba9925c1076b1fbe4f44af0baf2d28e3cae679e643887"},"schema_version":"1.0","source":{"id":"1910.08348","kind":"arxiv","version":2}},"canonical_sha256":"019de97aab4d3dc007e265eff0d5642ea0e8f30979670976e8e1804a3596a30e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"019de97aab4d3dc007e265eff0d5642ea0e8f30979670976e8e1804a3596a30e","first_computed_at":"2026-07-05T00:44:27.501503Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:27.501503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"raboE4U/lf6xeQrNgwv+LisOEk/xPWs+ljoS9OxmTPy7qTPqpXoyS6XjDUJAMf3D7YKGmAv3JA+DIl25Ui/DBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:27.502033Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.08348","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fb3b36492a7ab1b744e15eb21c13a8fafc85789774d486a9295d78647ef4339","sha256:734c4a3a6131dbf5576dbca8317bc853f5188d0de088e795762ab05d26e4d10d"],"state_sha256":"9b76e81fc4d88fbf9501d5c091b68bdb12e5db42c10e61db28fd0fbfdab64002"}