{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XWQLXNYS562GZLZ6LTOEHER274","short_pith_number":"pith:XWQLXNYS","schema_version":"1.0","canonical_sha256":"bda0bbb712efb46caf3e5cdc43923aff3ec0951f21d34bec2ce5cc4163dbdfcf","source":{"kind":"arxiv","id":"2104.08212","version":2},"attestation_state":"computed","paper":{"title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Benjamin Swanson, Chelsea Finn, Dmitry Kalashnikov, Jacob Varley, Karol Hausman, Rico Jonschkowski, Sergey Levine, Yevgen Chebotar","submitted_at":"2021-04-16T16:38:02Z","abstract_excerpt":"General-purpose robotic systems must master a large repertoire of diverse skills to be useful in a range of daily tasks. While reinforcement learning provides a powerful framework for acquiring individual behaviors, the time needed to acquire each skill makes the prospect of a generalist robot trained with RL daunting. In this paper, we study how a large-scale collective robotic learning system can acquire a repertoire of behaviors simultaneously, sharing exploration, experience, and representations across tasks. In this framework new tasks can be continuously instantiated from previously lear"},"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":"2104.08212","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-04-16T16:38:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3397cce9db9512c19585683a237c24bf1a0a52cf085a622f2293a5bfeff41a52","abstract_canon_sha256":"d65fdf8360c2aa9728f6ee85b82453fd6e945cc6512423af811ce9f2cc65ee51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:35:54.137806Z","signature_b64":"dryxqhte6AyngOfwBf+lGwNm1r/3eQmcV+7ygrLax1vSXFVRYYwbCHzkkEara5rEzcdIIJfE6+3RONho/zDeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bda0bbb712efb46caf3e5cdc43923aff3ec0951f21d34bec2ce5cc4163dbdfcf","last_reissued_at":"2026-07-05T02:35:54.137295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:35:54.137295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Benjamin Swanson, Chelsea Finn, Dmitry Kalashnikov, Jacob Varley, Karol Hausman, Rico Jonschkowski, Sergey Levine, Yevgen Chebotar","submitted_at":"2021-04-16T16:38:02Z","abstract_excerpt":"General-purpose robotic systems must master a large repertoire of diverse skills to be useful in a range of daily tasks. While reinforcement learning provides a powerful framework for acquiring individual behaviors, the time needed to acquire each skill makes the prospect of a generalist robot trained with RL daunting. In this paper, we study how a large-scale collective robotic learning system can acquire a repertoire of behaviors simultaneously, sharing exploration, experience, and representations across tasks. In this framework new tasks can be continuously instantiated from previously lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08212","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/2104.08212/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":"2104.08212","created_at":"2026-07-05T02:35:54.137364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.08212v2","created_at":"2026-07-05T02:35:54.137364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08212","created_at":"2026-07-05T02:35:54.137364+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWQLXNYS562G","created_at":"2026-07-05T02:35:54.137364+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWQLXNYS562GZLZ6","created_at":"2026-07-05T02:35:54.137364+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWQLXNYS","created_at":"2026-07-05T02:35:54.137364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21406","citing_title":"Robot Self-Improvement via Human-Video Dynamics Models","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19656","citing_title":"DF-ExpEnse: Diffusion Filtered Exploration for Sample Efficient Finetuning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07217","citing_title":"Robotic Policy Adaptation via Weight-Space Meta-Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00642","citing_title":"Coachable agents for interactive gameplay","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31682","citing_title":"HABIT: Human-Aware Behavior and Interaction Training Dataset for Robot Manipulation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00416","citing_title":"Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29662","citing_title":"SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14093","citing_title":"A Survey on Vision-Language-Action Models for Embodied AI","ref_index":165,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17486","citing_title":"DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization","ref_index":155,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17441","citing_title":"RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2302.11550","citing_title":"Scaling Robot Learning with Semantically Imagined Experience","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2310.17596","citing_title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2412.13877","citing_title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10345","citing_title":"TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2109.13396","citing_title":"Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":124,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02523","citing_title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05608","citing_title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2310.08864","citing_title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00416","citing_title":"Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XWQLXNYS562GZLZ6LTOEHER274","json":"https://pith.science/pith/XWQLXNYS562GZLZ6LTOEHER274.json","graph_json":"https://pith.science/api/pith-number/XWQLXNYS562GZLZ6LTOEHER274/graph.json","events_json":"https://pith.science/api/pith-number/XWQLXNYS562GZLZ6LTOEHER274/events.json","paper":"https://pith.science/paper/XWQLXNYS"},"agent_actions":{"view_html":"https://pith.science/pith/XWQLXNYS562GZLZ6LTOEHER274","download_json":"https://pith.science/pith/XWQLXNYS562GZLZ6LTOEHER274.json","view_paper":"https://pith.science/paper/XWQLXNYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.08212&json=true","fetch_graph":"https://pith.science/api/pith-number/XWQLXNYS562GZLZ6LTOEHER274/graph.json","fetch_events":"https://pith.science/api/pith-number/XWQLXNYS562GZLZ6LTOEHER274/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWQLXNYS562GZLZ6LTOEHER274/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWQLXNYS562GZLZ6LTOEHER274/action/storage_attestation","attest_author":"https://pith.science/pith/XWQLXNYS562GZLZ6LTOEHER274/action/author_attestation","sign_citation":"https://pith.science/pith/XWQLXNYS562GZLZ6LTOEHER274/action/citation_signature","submit_replication":"https://pith.science/pith/XWQLXNYS562GZLZ6LTOEHER274/action/replication_record"}},"created_at":"2026-07-05T02:35:54.137364+00:00","updated_at":"2026-07-05T02:35:54.137364+00:00"}