{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ACDIG6MHAU2BXO2BTU2UX6CDZ6","short_pith_number":"pith:ACDIG6MH","schema_version":"1.0","canonical_sha256":"008683798705341bbb419d354bf843cf8a174417b176bbadb71673277e83df68","source":{"kind":"arxiv","id":"1802.04325","version":2},"attestation_state":"computed","paper":{"title":"Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dane Corneil, Johanni Brea, Wulfram Gerstner","submitted_at":"2018-02-12T19:38:44Z","abstract_excerpt":"Modern reinforcement learning algorithms reach super-human performance on many board and video games, but they are sample inefficient, i.e. they typically require significantly more playing experience than humans to reach an equal performance level. To improve sample efficiency, an agent may build a model of the environment and use planning methods to update its policy. In this article we introduce Variational State Tabulation (VaST), which maps an environment with a high-dimensional state space (e.g. the space of visual inputs) to an abstract tabular model. Prioritized sweeping with small bac"},"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":"1802.04325","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T19:38:44Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"98a4b7784bf5cdfe8382e462a4d21a8085c36a67459a2e251b697d01f1908f8b","abstract_canon_sha256":"a6d2289c7d6da933f59df2bc292f77c442d2d7ee6ae6e14bb7c183b57b6a7688"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:44.916656Z","signature_b64":"G9YU9tuiciY55SEXsIG9lBY7Fbiq4Ja56vv3T4PGyybS/9tg/DDdihuGwkrJfNGnjOj5NBRHBhmCVZ9hNlm3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"008683798705341bbb419d354bf843cf8a174417b176bbadb71673277e83df68","last_reissued_at":"2026-05-18T00:13:44.915887Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:44.915887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dane Corneil, Johanni Brea, Wulfram Gerstner","submitted_at":"2018-02-12T19:38:44Z","abstract_excerpt":"Modern reinforcement learning algorithms reach super-human performance on many board and video games, but they are sample inefficient, i.e. they typically require significantly more playing experience than humans to reach an equal performance level. To improve sample efficiency, an agent may build a model of the environment and use planning methods to update its policy. In this article we introduce Variational State Tabulation (VaST), which maps an environment with a high-dimensional state space (e.g. the space of visual inputs) to an abstract tabular model. Prioritized sweeping with small bac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04325","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":""},"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":"1802.04325","created_at":"2026-05-18T00:13:44.916016+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04325v2","created_at":"2026-05-18T00:13:44.916016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04325","created_at":"2026-05-18T00:13:44.916016+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACDIG6MHAU2B","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACDIG6MHAU2BXO2B","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACDIG6MH","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ACDIG6MHAU2BXO2BTU2UX6CDZ6","json":"https://pith.science/pith/ACDIG6MHAU2BXO2BTU2UX6CDZ6.json","graph_json":"https://pith.science/api/pith-number/ACDIG6MHAU2BXO2BTU2UX6CDZ6/graph.json","events_json":"https://pith.science/api/pith-number/ACDIG6MHAU2BXO2BTU2UX6CDZ6/events.json","paper":"https://pith.science/paper/ACDIG6MH"},"agent_actions":{"view_html":"https://pith.science/pith/ACDIG6MHAU2BXO2BTU2UX6CDZ6","download_json":"https://pith.science/pith/ACDIG6MHAU2BXO2BTU2UX6CDZ6.json","view_paper":"https://pith.science/paper/ACDIG6MH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04325&json=true","fetch_graph":"https://pith.science/api/pith-number/ACDIG6MHAU2BXO2BTU2UX6CDZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/ACDIG6MHAU2BXO2BTU2UX6CDZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACDIG6MHAU2BXO2BTU2UX6CDZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACDIG6MHAU2BXO2BTU2UX6CDZ6/action/storage_attestation","attest_author":"https://pith.science/pith/ACDIG6MHAU2BXO2BTU2UX6CDZ6/action/author_attestation","sign_citation":"https://pith.science/pith/ACDIG6MHAU2BXO2BTU2UX6CDZ6/action/citation_signature","submit_replication":"https://pith.science/pith/ACDIG6MHAU2BXO2BTU2UX6CDZ6/action/replication_record"}},"created_at":"2026-05-18T00:13:44.916016+00:00","updated_at":"2026-05-18T00:13:44.916016+00:00"}