{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NPOR4RDRIW3G7UAOGDW4W3MS4H","short_pith_number":"pith:NPOR4RDR","schema_version":"1.0","canonical_sha256":"6bdd1e447145b66fd00e30edcb6d92e1fbce071031c307390282f638db36818e","source":{"kind":"arxiv","id":"1910.10897","version":2},"attestation_state":"computed","paper":{"title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adithya Bellathur, Avnish Narayan, Chelsea Finn, Deirdre Quillen, Hayden Shively, Karol Hausman, Ryan Julian, Sergey Levine, Tianhe Yu, Zhanpeng He","submitted_at":"2019-10-24T03:19:46Z","abstract_excerpt":"Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task distributions that are very narrow. For example, a commonly used meta-reinforcement learning benchmark uses different running velocities for a simulated robot as different tasks. When policies are meta-trained on such narrow task distributions, they cannot possibly generalize to more quickly acquire entirely new tasks. Therefore, if the aim of these methods is "},"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":"1910.10897","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-24T03:19:46Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"73f649294d987729a645a51ea087110e0ece6dbf9123102320cf0e0857c020b0","abstract_canon_sha256":"dbfdd9c98d1d4287543c96ce8a3f5c3274f7fc7c2b3f42b0d705fc8b818d358f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:09.357732Z","signature_b64":"RKZQ1xF1di1bBp9U4ST+yeDIx6jFX1L/WDVVrFxi9d+armb7aSeo4E6PX40UYTyANw/9hbmOw9JgVXxJZQnCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bdd1e447145b66fd00e30edcb6d92e1fbce071031c307390282f638db36818e","last_reissued_at":"2026-07-05T02:49:09.357184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:09.357184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adithya Bellathur, Avnish Narayan, Chelsea Finn, Deirdre Quillen, Hayden Shively, Karol Hausman, Ryan Julian, Sergey Levine, Tianhe Yu, Zhanpeng He","submitted_at":"2019-10-24T03:19:46Z","abstract_excerpt":"Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task distributions that are very narrow. For example, a commonly used meta-reinforcement learning benchmark uses different running velocities for a simulated robot as different tasks. When policies are meta-trained on such narrow task distributions, they cannot possibly generalize to more quickly acquire entirely new tasks. Therefore, if the aim of these methods is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.10897","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.10897/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1910.10897","created_at":"2026-07-05T02:49:09.357244+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.10897v2","created_at":"2026-07-05T02:49:09.357244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.10897","created_at":"2026-07-05T02:49:09.357244+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPOR4RDRIW3G","created_at":"2026-07-05T02:49:09.357244+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPOR4RDRIW3G7UAO","created_at":"2026-07-05T02:49:09.357244+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPOR4RDR","created_at":"2026-07-05T02:49:09.357244+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27348","citing_title":"Bridging Performance and Generalization in Reinforcement Learning for Agile Flight","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20272","citing_title":"Efficiently Linking Real Scenes with Synthetic Data Generation for AI-based Cognitive Robotics and Computer Vision Applications","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":190,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19328","citing_title":"UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17511","citing_title":"MagicSim: A Unified Infrastructure for Executable Embodied Interaction","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17446","citing_title":"AnnotateAnything: Automatic Annotation of 3D Assets for Robot Manipulation","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05331","citing_title":"A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14598","citing_title":"DSSP: Diffusion State Space Policy with Full-History Encoding","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10236","citing_title":"When Does Non-Uniform Replay Matter in Reinforcement Learning?","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18617","citing_title":"ManiSoft: Towards Vision-Language Manipulation for Soft Continuum Robotics","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20869","citing_title":"Model-Based Reinforcement Learning under Random Observation Delays","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2512.20974","citing_title":"Generalised Linear Models in Deep Bayesian RL with Learnable Basis Functions","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02078","citing_title":"Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02349","citing_title":"OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09860","citing_title":"RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2310.16828","citing_title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10236","citing_title":"When Does Non-Uniform Replay Matter in Reinforcement Learning?","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":221,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09727","citing_title":"One for All: A Non-Linear Transformer can Enable Cross-Domain Generalization for In-Context Reinforcement Learning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10236","citing_title":"When Does Non-Uniform Replay Matter in Reinforcement Learning?","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23001","citing_title":"Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2407.17032","citing_title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09860","citing_title":"RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17876","citing_title":"OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPOR4RDRIW3G7UAOGDW4W3MS4H","json":"https://pith.science/pith/NPOR4RDRIW3G7UAOGDW4W3MS4H.json","graph_json":"https://pith.science/api/pith-number/NPOR4RDRIW3G7UAOGDW4W3MS4H/graph.json","events_json":"https://pith.science/api/pith-number/NPOR4RDRIW3G7UAOGDW4W3MS4H/events.json","paper":"https://pith.science/paper/NPOR4RDR"},"agent_actions":{"view_html":"https://pith.science/pith/NPOR4RDRIW3G7UAOGDW4W3MS4H","download_json":"https://pith.science/pith/NPOR4RDRIW3G7UAOGDW4W3MS4H.json","view_paper":"https://pith.science/paper/NPOR4RDR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.10897&json=true","fetch_graph":"https://pith.science/api/pith-number/NPOR4RDRIW3G7UAOGDW4W3MS4H/graph.json","fetch_events":"https://pith.science/api/pith-number/NPOR4RDRIW3G7UAOGDW4W3MS4H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPOR4RDRIW3G7UAOGDW4W3MS4H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPOR4RDRIW3G7UAOGDW4W3MS4H/action/storage_attestation","attest_author":"https://pith.science/pith/NPOR4RDRIW3G7UAOGDW4W3MS4H/action/author_attestation","sign_citation":"https://pith.science/pith/NPOR4RDRIW3G7UAOGDW4W3MS4H/action/citation_signature","submit_replication":"https://pith.science/pith/NPOR4RDRIW3G7UAOGDW4W3MS4H/action/replication_record"}},"created_at":"2026-07-05T02:49:09.357244+00:00","updated_at":"2026-07-05T02:49:09.357244+00:00"}