{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CJOGZAZJDZVNMAA6ZOBAMNU2BY","short_pith_number":"pith:CJOGZAZJ","schema_version":"1.0","canonical_sha256":"125c6c83291e6ad6001ecb8206369a0e206e759a7eef15548d2d19484c637ce5","source":{"kind":"arxiv","id":"1802.03006","version":1},"attestation_state":"computed","paper":{"title":"Learning and Querying Fast Generative Models for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daan Wierstra, Danilo Rezende, David P. Reichert, Demis Hassabis, Fabio Viola, Frederic Besse, Karol Gregor, Lars Buesing, Sebastien Racaniere, S. M. Ali Eslami, Theophane Weber","submitted_at":"2018-02-08T18:54:44Z","abstract_excerpt":"A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models. We show that carefully designed generative models that learn and operate on compact state representations, so-called state-space models, substantially reduce the computational costs for predicting outcomes of sequences of actions. Extensive experiments establish that state-space models accurately capture the dynamics of Atari games from the Arcade Learning Environment from raw pixels. The computational speed-up of state-space models while maintaining high accur"},"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":"1802.03006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-08T18:54:44Z","cross_cats_sorted":[],"title_canon_sha256":"0776a855dbedb0662f6f40418852d950a06b1fe728cc9df506cd662d3a8c1496","abstract_canon_sha256":"ccd071c25048468c18a1d1f41901e1f4ee69523d15fcfd183e190e78747673c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:02.616861Z","signature_b64":"oBo9Nl4W4PNYkRDFLUHPiFwZsDz0zKX/lEgCmH2jBw5tuGqghdN3iz511m9uPtEontG6eEcD8mIng0OSojtVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"125c6c83291e6ad6001ecb8206369a0e206e759a7eef15548d2d19484c637ce5","last_reissued_at":"2026-05-18T00:24:02.616259Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:02.616259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning and Querying Fast Generative Models for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daan Wierstra, Danilo Rezende, David P. Reichert, Demis Hassabis, Fabio Viola, Frederic Besse, Karol Gregor, Lars Buesing, Sebastien Racaniere, S. M. Ali Eslami, Theophane Weber","submitted_at":"2018-02-08T18:54:44Z","abstract_excerpt":"A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models. We show that carefully designed generative models that learn and operate on compact state representations, so-called state-space models, substantially reduce the computational costs for predicting outcomes of sequences of actions. Extensive experiments establish that state-space models accurately capture the dynamics of Atari games from the Arcade Learning Environment from raw pixels. The computational speed-up of state-space models while maintaining high accur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03006","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":"1802.03006","created_at":"2026-05-18T00:24:02.616348+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03006v1","created_at":"2026-05-18T00:24:02.616348+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03006","created_at":"2026-05-18T00:24:02.616348+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJOGZAZJDZVN","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJOGZAZJDZVNMAA6","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJOGZAZJ","created_at":"2026-05-18T12:32:16.446611+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":29,"is_internal_anchor":true},{"citing_arxiv_id":"1906.09510","citing_title":"Learning Belief Representations for Imitation Learning in POMDPs","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"1911.08265","citing_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2010.02193","citing_title":"Mastering Atari with Discrete World Models","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"1912.01603","citing_title":"Dream to Control: Learning Behaviors by Latent Imagination","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":220,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CJOGZAZJDZVNMAA6ZOBAMNU2BY","json":"https://pith.science/pith/CJOGZAZJDZVNMAA6ZOBAMNU2BY.json","graph_json":"https://pith.science/api/pith-number/CJOGZAZJDZVNMAA6ZOBAMNU2BY/graph.json","events_json":"https://pith.science/api/pith-number/CJOGZAZJDZVNMAA6ZOBAMNU2BY/events.json","paper":"https://pith.science/paper/CJOGZAZJ"},"agent_actions":{"view_html":"https://pith.science/pith/CJOGZAZJDZVNMAA6ZOBAMNU2BY","download_json":"https://pith.science/pith/CJOGZAZJDZVNMAA6ZOBAMNU2BY.json","view_paper":"https://pith.science/paper/CJOGZAZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03006&json=true","fetch_graph":"https://pith.science/api/pith-number/CJOGZAZJDZVNMAA6ZOBAMNU2BY/graph.json","fetch_events":"https://pith.science/api/pith-number/CJOGZAZJDZVNMAA6ZOBAMNU2BY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJOGZAZJDZVNMAA6ZOBAMNU2BY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJOGZAZJDZVNMAA6ZOBAMNU2BY/action/storage_attestation","attest_author":"https://pith.science/pith/CJOGZAZJDZVNMAA6ZOBAMNU2BY/action/author_attestation","sign_citation":"https://pith.science/pith/CJOGZAZJDZVNMAA6ZOBAMNU2BY/action/citation_signature","submit_replication":"https://pith.science/pith/CJOGZAZJDZVNMAA6ZOBAMNU2BY/action/replication_record"}},"created_at":"2026-05-18T00:24:02.616348+00:00","updated_at":"2026-05-18T00:24:02.616348+00:00"}