{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MVPSHW2B6TUO7R6OFIV3BF2QT5","short_pith_number":"pith:MVPSHW2B","schema_version":"1.0","canonical_sha256":"655f23db41f4e8efc7ce2a2bb097509f4367948527aa9c6e1bde09ddbf583180","source":{"kind":"arxiv","id":"2006.06874","version":1},"attestation_state":"computed","paper":{"title":"Learning to Play by Imitating Humans","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Corey Lynch, Pierre Sermanet, Rostam Dinyari","submitted_at":"2020-06-11T23:28:54Z","abstract_excerpt":"Acquiring multiple skills has commonly involved collecting a large number of expert demonstrations per task or engineering custom reward functions. Recently it has been shown that it is possible to acquire a diverse set of skills by self-supervising control on top of human teleoperated play data. Play is rich in state space coverage and a policy trained on this data can generalize to specific tasks at test time outperforming policies trained on individual expert task demonstrations. In this work, we explore the question of whether robots can learn to play to autonomously generate play data tha"},"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":"2006.06874","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-06-11T23:28:54Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"7efd254b22ad7c3e937875443f14109adf2509fbcb4fc9058f14c669b847dcfe","abstract_canon_sha256":"c24a593feeb5eafa26f507c9033654abe3bc746d875a6f0b6989231a83759f1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:47.777806Z","signature_b64":"/x/8FiGoURuIUwDBZIpCZHuvPZTCrpGKr41BCreBhyeaykufG2fUoo4lZwdW3Z0GxdDqScIIX9pew5IFuZ7XDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"655f23db41f4e8efc7ce2a2bb097509f4367948527aa9c6e1bde09ddbf583180","last_reissued_at":"2026-07-05T01:09:47.777391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:47.777391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Play by Imitating Humans","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Corey Lynch, Pierre Sermanet, Rostam Dinyari","submitted_at":"2020-06-11T23:28:54Z","abstract_excerpt":"Acquiring multiple skills has commonly involved collecting a large number of expert demonstrations per task or engineering custom reward functions. Recently it has been shown that it is possible to acquire a diverse set of skills by self-supervising control on top of human teleoperated play data. Play is rich in state space coverage and a policy trained on this data can generalize to specific tasks at test time outperforming policies trained on individual expert task demonstrations. In this work, we explore the question of whether robots can learn to play to autonomously generate play data tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06874","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.06874/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":"2006.06874","created_at":"2026-07-05T01:09:47.777453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.06874v1","created_at":"2026-07-05T01:09:47.777453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06874","created_at":"2026-07-05T01:09:47.777453+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVPSHW2B6TUO","created_at":"2026-07-05T01:09:47.777453+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVPSHW2B6TUO7R6O","created_at":"2026-07-05T01:09:47.777453+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVPSHW2B","created_at":"2026-07-05T01:09:47.777453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVPSHW2B6TUO7R6OFIV3BF2QT5","json":"https://pith.science/pith/MVPSHW2B6TUO7R6OFIV3BF2QT5.json","graph_json":"https://pith.science/api/pith-number/MVPSHW2B6TUO7R6OFIV3BF2QT5/graph.json","events_json":"https://pith.science/api/pith-number/MVPSHW2B6TUO7R6OFIV3BF2QT5/events.json","paper":"https://pith.science/paper/MVPSHW2B"},"agent_actions":{"view_html":"https://pith.science/pith/MVPSHW2B6TUO7R6OFIV3BF2QT5","download_json":"https://pith.science/pith/MVPSHW2B6TUO7R6OFIV3BF2QT5.json","view_paper":"https://pith.science/paper/MVPSHW2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.06874&json=true","fetch_graph":"https://pith.science/api/pith-number/MVPSHW2B6TUO7R6OFIV3BF2QT5/graph.json","fetch_events":"https://pith.science/api/pith-number/MVPSHW2B6TUO7R6OFIV3BF2QT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVPSHW2B6TUO7R6OFIV3BF2QT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVPSHW2B6TUO7R6OFIV3BF2QT5/action/storage_attestation","attest_author":"https://pith.science/pith/MVPSHW2B6TUO7R6OFIV3BF2QT5/action/author_attestation","sign_citation":"https://pith.science/pith/MVPSHW2B6TUO7R6OFIV3BF2QT5/action/citation_signature","submit_replication":"https://pith.science/pith/MVPSHW2B6TUO7R6OFIV3BF2QT5/action/replication_record"}},"created_at":"2026-07-05T01:09:47.777453+00:00","updated_at":"2026-07-05T01:09:47.777453+00:00"}