{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VEUYHKKF5CW4OG6I6F6RHP7IIM","short_pith_number":"pith:VEUYHKKF","schema_version":"1.0","canonical_sha256":"a92983a945e8adc71bc8f17d13bfe843206c9122cf60f6994cea242e255f566d","source":{"kind":"arxiv","id":"1806.02426","version":1},"attestation_state":"computed","paper":{"title":"Deep Variational Reinforcement Learning for POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Wood, Luisa Zintgraf, Maximilian Igl, Shimon Whiteson, Tuan Anh Le","submitted_at":"2018-06-06T21:09:39Z","abstract_excerpt":"Many real-world sequential decision making problems are partially observable by nature, and the environment model is typically unknown. Consequently, there is great need for reinforcement learning methods that can tackle such problems given only a stream of incomplete and noisy observations. In this paper, we propose deep variational reinforcement learning (DVRL), which introduces an inductive bias that allows an agent to learn a generative model of the environment and perform inference in that model to effectively aggregate the available information. We develop an n-step approximation to the "},"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":"1806.02426","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-06T21:09:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"90e35c23333dfcc822e324481a2166ea4ac2e446a3724d7467372e8a7e2610fe","abstract_canon_sha256":"325e0ee5a8e3e6548cfaec032bc28aaead251dd38f87adc29dcdadcbc0b0c600"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:56.863563Z","signature_b64":"dP806tJEaOa/5KBYy85r0CqskbeP3OcGC7S2q4iJU7LSDcnIQz6JMceUF7G+mA3kKeZh54Bbn6KfqLPyRm0LCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a92983a945e8adc71bc8f17d13bfe843206c9122cf60f6994cea242e255f566d","last_reissued_at":"2026-05-18T00:13:56.862840Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:56.862840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Variational Reinforcement Learning for POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Wood, Luisa Zintgraf, Maximilian Igl, Shimon Whiteson, Tuan Anh Le","submitted_at":"2018-06-06T21:09:39Z","abstract_excerpt":"Many real-world sequential decision making problems are partially observable by nature, and the environment model is typically unknown. Consequently, there is great need for reinforcement learning methods that can tackle such problems given only a stream of incomplete and noisy observations. In this paper, we propose deep variational reinforcement learning (DVRL), which introduces an inductive bias that allows an agent to learn a generative model of the environment and perform inference in that model to effectively aggregate the available information. We develop an n-step approximation to the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02426","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1806.02426","created_at":"2026-05-18T00:13:56.862964+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.02426v1","created_at":"2026-05-18T00:13:56.862964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02426","created_at":"2026-05-18T00:13:56.862964+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEUYHKKF5CW4","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEUYHKKF5CW4OG6I","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEUYHKKF","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1906.09237","citing_title":"Shaping Belief States with Generative Environment Models for RL","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"1906.09510","citing_title":"Learning Belief Representations for Imitation Learning in POMDPs","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"1907.09475","citing_title":"Deep Reinforcement Learning for Clinical Decision Support: A Brief Survey","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2010.02193","citing_title":"Mastering Atari with Discrete World Models","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09671","citing_title":"Belief-State RWKV for Reinforcement Learning under Partial Observability","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":188,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEUYHKKF5CW4OG6I6F6RHP7IIM","json":"https://pith.science/pith/VEUYHKKF5CW4OG6I6F6RHP7IIM.json","graph_json":"https://pith.science/api/pith-number/VEUYHKKF5CW4OG6I6F6RHP7IIM/graph.json","events_json":"https://pith.science/api/pith-number/VEUYHKKF5CW4OG6I6F6RHP7IIM/events.json","paper":"https://pith.science/paper/VEUYHKKF"},"agent_actions":{"view_html":"https://pith.science/pith/VEUYHKKF5CW4OG6I6F6RHP7IIM","download_json":"https://pith.science/pith/VEUYHKKF5CW4OG6I6F6RHP7IIM.json","view_paper":"https://pith.science/paper/VEUYHKKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.02426&json=true","fetch_graph":"https://pith.science/api/pith-number/VEUYHKKF5CW4OG6I6F6RHP7IIM/graph.json","fetch_events":"https://pith.science/api/pith-number/VEUYHKKF5CW4OG6I6F6RHP7IIM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEUYHKKF5CW4OG6I6F6RHP7IIM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEUYHKKF5CW4OG6I6F6RHP7IIM/action/storage_attestation","attest_author":"https://pith.science/pith/VEUYHKKF5CW4OG6I6F6RHP7IIM/action/author_attestation","sign_citation":"https://pith.science/pith/VEUYHKKF5CW4OG6I6F6RHP7IIM/action/citation_signature","submit_replication":"https://pith.science/pith/VEUYHKKF5CW4OG6I6F6RHP7IIM/action/replication_record"}},"created_at":"2026-05-18T00:13:56.862964+00:00","updated_at":"2026-05-18T00:13:56.862964+00:00"}