{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AGO6S6VLJU64AB7CMXX7BVLEF2","short_pith_number":"pith:AGO6S6VL","schema_version":"1.0","canonical_sha256":"019de97aab4d3dc007e265eff0d5642ea0e8f30979670976e8e1804a3596a30e","source":{"kind":"arxiv","id":"1910.08348","version":2},"attestation_state":"computed","paper":{"title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Katja Hofmann, Kyriacos Shiarlis, Luisa Zintgraf, Maximilian Igl, Sebastian Schulze, Shimon Whiteson, Yarin Gal","submitted_at":"2019-10-18T11:44:59Z","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-"},"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":"1910.08348","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-18T11:44:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fa0dc4365b5c488b202ba9925c1076b1fbe4f44af0baf2d28e3cae679e643887","abstract_canon_sha256":"adb92dfc5245d6f67d222e7a7908641a27099b80ece2bcdbcb73cc2db0fe99df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:27.502033Z","signature_b64":"raboE4U/lf6xeQrNgwv+LisOEk/xPWs+ljoS9OxmTPy7qTPqpXoyS6XjDUJAMf3D7YKGmAv3JA+DIl25Ui/DBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"019de97aab4d3dc007e265eff0d5642ea0e8f30979670976e8e1804a3596a30e","last_reissued_at":"2026-07-05T00:44:27.501503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:27.501503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Katja Hofmann, Kyriacos Shiarlis, Luisa Zintgraf, Maximilian Igl, Sebastian Schulze, Shimon Whiteson, Yarin Gal","submitted_at":"2019-10-18T11:44:59Z","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-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.08348","kind":"arxiv","version":2},"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/1910.08348/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":"1910.08348","created_at":"2026-07-05T00:44:27.501568+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.08348v2","created_at":"2026-07-05T00:44:27.501568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.08348","created_at":"2026-07-05T00:44:27.501568+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGO6S6VLJU64","created_at":"2026-07-05T00:44:27.501568+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGO6S6VLJU64AB7C","created_at":"2026-07-05T00:44:27.501568+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGO6S6VL","created_at":"2026-07-05T00:44:27.501568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26025","citing_title":"In-Context World Modeling for Robotic Control","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26025","citing_title":"In-Context World Modeling for Robotic Control","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12890","citing_title":"Learning to Adapt: Representation-Based Reinforcement Learning for Multi-Task Skill Transfer","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22082","citing_title":"CoRMA: Contrastive RMA for Contact-Rich Meta-Adaptation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00780","citing_title":"Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02834","citing_title":"Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22082","citing_title":"CoRMA: Contrastive RMA for Contact-Rich Meta-Adaptation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19837","citing_title":"Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent","ref_index":206,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06992","citing_title":"Why Does Agentic Safety Fail to Generalize Across Tasks?","ref_index":130,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AGO6S6VLJU64AB7CMXX7BVLEF2","json":"https://pith.science/pith/AGO6S6VLJU64AB7CMXX7BVLEF2.json","graph_json":"https://pith.science/api/pith-number/AGO6S6VLJU64AB7CMXX7BVLEF2/graph.json","events_json":"https://pith.science/api/pith-number/AGO6S6VLJU64AB7CMXX7BVLEF2/events.json","paper":"https://pith.science/paper/AGO6S6VL"},"agent_actions":{"view_html":"https://pith.science/pith/AGO6S6VLJU64AB7CMXX7BVLEF2","download_json":"https://pith.science/pith/AGO6S6VLJU64AB7CMXX7BVLEF2.json","view_paper":"https://pith.science/paper/AGO6S6VL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.08348&json=true","fetch_graph":"https://pith.science/api/pith-number/AGO6S6VLJU64AB7CMXX7BVLEF2/graph.json","fetch_events":"https://pith.science/api/pith-number/AGO6S6VLJU64AB7CMXX7BVLEF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGO6S6VLJU64AB7CMXX7BVLEF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGO6S6VLJU64AB7CMXX7BVLEF2/action/storage_attestation","attest_author":"https://pith.science/pith/AGO6S6VLJU64AB7CMXX7BVLEF2/action/author_attestation","sign_citation":"https://pith.science/pith/AGO6S6VLJU64AB7CMXX7BVLEF2/action/citation_signature","submit_replication":"https://pith.science/pith/AGO6S6VLJU64AB7CMXX7BVLEF2/action/replication_record"}},"created_at":"2026-07-05T00:44:27.501568+00:00","updated_at":"2026-07-05T00:44:27.501568+00:00"}