{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SAGDKD333HRHHULVD3XITPJN7O","short_pith_number":"pith:SAGDKD33","schema_version":"1.0","canonical_sha256":"900c350f7bd9e273d1751eee89bd2dfb86745d9123f8e89f2b8a6ab036638cba","source":{"kind":"arxiv","id":"1812.00568","version":1},"attestation_state":"computed","paper":{"title":"Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alex Lee, Annie Xie, Chelsea Finn, Frederik Ebert, Sergey Levine, Sudeep Dasari","submitted_at":"2018-12-03T06:06:25Z","abstract_excerpt":"Deep reinforcement learning (RL) algorithms can learn complex robotic skills from raw sensory inputs, but have yet to achieve the kind of broad generalization and applicability demonstrated by deep learning methods in supervised domains. We present a deep RL method that is practical for real-world robotics tasks, such as robotic manipulation, and generalizes effectively to never-before-seen tasks and objects. In these settings, ground truth reward signals are typically unavailable, and we therefore propose a self-supervised model-based approach, where a predictive model learns to directly pred"},"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":"1812.00568","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-12-03T06:06:25Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"b8374a82d4efaa99472283b94e83843e9553f7f7db99d1a5d5a56665c4bfe856","abstract_canon_sha256":"639ca20519d1500df43df23544c63f22ca54070e56103128250c769bf234d5fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:20.994551Z","signature_b64":"K4QP4708F1gDMkmxFbooLxs2cyLYPBVOEzTqMf9LYWy57lNE4DlDmzIunPEunpfE9cv3Fq+v9rnduAv9L24DCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"900c350f7bd9e273d1751eee89bd2dfb86745d9123f8e89f2b8a6ab036638cba","last_reissued_at":"2026-05-17T23:59:20.994046Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:20.994046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alex Lee, Annie Xie, Chelsea Finn, Frederik Ebert, Sergey Levine, Sudeep Dasari","submitted_at":"2018-12-03T06:06:25Z","abstract_excerpt":"Deep reinforcement learning (RL) algorithms can learn complex robotic skills from raw sensory inputs, but have yet to achieve the kind of broad generalization and applicability demonstrated by deep learning methods in supervised domains. We present a deep RL method that is practical for real-world robotics tasks, such as robotic manipulation, and generalizes effectively to never-before-seen tasks and objects. In these settings, ground truth reward signals are typically unavailable, and we therefore propose a self-supervised model-based approach, where a predictive model learns to directly pred"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00568","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":"1812.00568","created_at":"2026-05-17T23:59:20.994119+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.00568v1","created_at":"2026-05-17T23:59:20.994119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00568","created_at":"2026-05-17T23:59:20.994119+00:00"},{"alias_kind":"pith_short_12","alias_value":"SAGDKD333HRH","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"SAGDKD333HRHHULV","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"SAGDKD33","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":31,"internal_anchor_count":24,"sample":[{"citing_arxiv_id":"2606.04130","citing_title":"CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02486","citing_title":"Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2606.01626","citing_title":"IMWM: Intuition Models Complement World Models for Latent Planning","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00267","citing_title":"StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15477","citing_title":"EgoExo-WM: Unlocking Exo Video for Ego World Models","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00412","citing_title":"Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00089","citing_title":"Can Predicted Dynamics Exist in the Physical World?","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2606.29908","citing_title":"Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25346","citing_title":"Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00664","citing_title":"SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2606.01027","citing_title":"$\\tau_0$-WM: A Unified Video-Action World Model for Robotic Manipulation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"1906.10182","citing_title":"Planning Robot Motion using Deep Visual Prediction","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"1906.12061","citing_title":"Learning to Cope with Adversarial Attacks","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02050","citing_title":"Reasoning and Generalization in RL: A Tool Use Perspective","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2603.14392","citing_title":"WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15477","citing_title":"EgoExo-WM: Unlocking Exo Video for Ego World Models","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2506.09981","citing_title":"ReSim: Reliable World Simulation for Autonomous Driving","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"1910.11215","citing_title":"RoboNet: Large-Scale Multi-Robot Learning","ref_index":7,"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":15,"is_internal_anchor":true},{"citing_arxiv_id":"2310.10639","citing_title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2510.10125","citing_title":"Ctrl-World: A Controllable Generative World Model for Robot Manipulation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2508.05635","citing_title":"Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2211.15657","citing_title":"Is Conditional Generative Modeling all you need for Decision-Making?","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2603.09030","citing_title":"PlayWorld: Learning Robot World Models from Autonomous Play","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2109.13396","citing_title":"Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SAGDKD333HRHHULVD3XITPJN7O","json":"https://pith.science/pith/SAGDKD333HRHHULVD3XITPJN7O.json","graph_json":"https://pith.science/api/pith-number/SAGDKD333HRHHULVD3XITPJN7O/graph.json","events_json":"https://pith.science/api/pith-number/SAGDKD333HRHHULVD3XITPJN7O/events.json","paper":"https://pith.science/paper/SAGDKD33"},"agent_actions":{"view_html":"https://pith.science/pith/SAGDKD333HRHHULVD3XITPJN7O","download_json":"https://pith.science/pith/SAGDKD333HRHHULVD3XITPJN7O.json","view_paper":"https://pith.science/paper/SAGDKD33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.00568&json=true","fetch_graph":"https://pith.science/api/pith-number/SAGDKD333HRHHULVD3XITPJN7O/graph.json","fetch_events":"https://pith.science/api/pith-number/SAGDKD333HRHHULVD3XITPJN7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SAGDKD333HRHHULVD3XITPJN7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SAGDKD333HRHHULVD3XITPJN7O/action/storage_attestation","attest_author":"https://pith.science/pith/SAGDKD333HRHHULVD3XITPJN7O/action/author_attestation","sign_citation":"https://pith.science/pith/SAGDKD333HRHHULVD3XITPJN7O/action/citation_signature","submit_replication":"https://pith.science/pith/SAGDKD333HRHHULVD3XITPJN7O/action/replication_record"}},"created_at":"2026-05-17T23:59:20.994119+00:00","updated_at":"2026-05-17T23:59:20.994119+00:00"}