{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WVVDZIBB24T6SMPO5ZSOVJNRMA","short_pith_number":"pith:WVVDZIBB","schema_version":"1.0","canonical_sha256":"b56a3ca021d727e931eeee64eaa5b1601eab476f7ec297d701d603744897e9ca","source":{"kind":"arxiv","id":"1811.04551","version":5},"attestation_state":"computed","paper":{"title":"Learning Latent Dynamics for Planning from Pixels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Danijar Hafner, David Ha, Honglak Lee, Ian Fischer, James Davidson, Ruben Villegas, Timothy Lillicrap","submitted_at":"2018-11-12T04:30:10Z","abstract_excerpt":"Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especially in image-based domains. We propose the Deep Planning Network (PlaNet), a purely model-based agent that learns the environment dynamics from images and chooses actions through fast online planning in latent space. To achieve high performance, the dynamics model must accurately p"},"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":"1811.04551","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-12T04:30:10Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"32f5a5ba00cf08245c785ace93bc921a1329ce01785eb99add050fbf68952b2c","abstract_canon_sha256":"996464752da24263bcb0e28c31b15eeb860b874b0efb0717b7da3ee54acf72e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:07.442449Z","signature_b64":"aqt3W/6ozS7jXKGL5YpeDwsx2bzuf8t0on/0c3P+ZVPUaJcKyJ48GWXC6Ni6su4E3Olzyuy05foPMUieQR4RCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b56a3ca021d727e931eeee64eaa5b1601eab476f7ec297d701d603744897e9ca","last_reissued_at":"2026-05-17T23:44:07.441905Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:07.441905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Latent Dynamics for Planning from Pixels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Danijar Hafner, David Ha, Honglak Lee, Ian Fischer, James Davidson, Ruben Villegas, Timothy Lillicrap","submitted_at":"2018-11-12T04:30:10Z","abstract_excerpt":"Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especially in image-based domains. We propose the Deep Planning Network (PlaNet), a purely model-based agent that learns the environment dynamics from images and chooses actions through fast online planning in latent space. To achieve high performance, the dynamics model must accurately p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.04551","kind":"arxiv","version":5},"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":"1811.04551","created_at":"2026-05-17T23:44:07.441993+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.04551v5","created_at":"2026-05-17T23:44:07.441993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.04551","created_at":"2026-05-17T23:44:07.441993+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVVDZIBB24T6","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVVDZIBB24T6SMPO","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVVDZIBB","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":14,"sample":[{"citing_arxiv_id":"1906.08649","citing_title":"Exploring Model-based Planning with Policy Networks","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"1906.09237","citing_title":"Shaping Belief States with Generative Environment Models for RL","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00664","citing_title":"Learning World Graphs to Accelerate Hierarchical Reinforcement Learning","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"1907.08040","citing_title":"Convolutional Reservoir Computing for World Models","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2504.03353","citing_title":"Decentralized Collective World Model for Emergent Communication and Coordination","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19376","citing_title":"Generative Recursive Reasoning","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19376","citing_title":"Generative Recursive Reasoning","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2510.23026","citing_title":"Mixed-Density Diffuser: Efficient Planning with Non-Uniform Temporal Resolution","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2411.04983","citing_title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","ref_index":20,"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":14,"is_internal_anchor":true},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":131,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08512","citing_title":"MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2509.24527","citing_title":"Training Agents Inside of Scalable World Models","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2010.02193","citing_title":"Mastering Atari with Discrete World Models","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04974","citing_title":"From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08512","citing_title":"MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09364","citing_title":"Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"1912.01603","citing_title":"Dream to Control: Learning Behaviors by Latent Imagination","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":223,"is_internal_anchor":false},{"citing_arxiv_id":"2005.01643","citing_title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","ref_index":155,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10333","citing_title":"Zero-shot World Models Are Developmentally Efficient Learners","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01694","citing_title":"Latent State Design for World Models under Sufficiency Constraints","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2301.04104","citing_title":"Mastering Diverse Domains through World Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14811","citing_title":"Learning Ad Hoc Network Dynamics via Graph-Structured World Models","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WVVDZIBB24T6SMPO5ZSOVJNRMA","json":"https://pith.science/pith/WVVDZIBB24T6SMPO5ZSOVJNRMA.json","graph_json":"https://pith.science/api/pith-number/WVVDZIBB24T6SMPO5ZSOVJNRMA/graph.json","events_json":"https://pith.science/api/pith-number/WVVDZIBB24T6SMPO5ZSOVJNRMA/events.json","paper":"https://pith.science/paper/WVVDZIBB"},"agent_actions":{"view_html":"https://pith.science/pith/WVVDZIBB24T6SMPO5ZSOVJNRMA","download_json":"https://pith.science/pith/WVVDZIBB24T6SMPO5ZSOVJNRMA.json","view_paper":"https://pith.science/paper/WVVDZIBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.04551&json=true","fetch_graph":"https://pith.science/api/pith-number/WVVDZIBB24T6SMPO5ZSOVJNRMA/graph.json","fetch_events":"https://pith.science/api/pith-number/WVVDZIBB24T6SMPO5ZSOVJNRMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVVDZIBB24T6SMPO5ZSOVJNRMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVVDZIBB24T6SMPO5ZSOVJNRMA/action/storage_attestation","attest_author":"https://pith.science/pith/WVVDZIBB24T6SMPO5ZSOVJNRMA/action/author_attestation","sign_citation":"https://pith.science/pith/WVVDZIBB24T6SMPO5ZSOVJNRMA/action/citation_signature","submit_replication":"https://pith.science/pith/WVVDZIBB24T6SMPO5ZSOVJNRMA/action/replication_record"}},"created_at":"2026-05-17T23:44:07.441993+00:00","updated_at":"2026-05-17T23:44:07.441993+00:00"}