{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:F2SKHER4BOF4DYNNYTU2G2HEUB","short_pith_number":"pith:F2SKHER4","schema_version":"1.0","canonical_sha256":"2ea4a3923c0b8bc1e1adc4e9a368e4a07e190fc1359f217048fae4a92784ca37","source":{"kind":"arxiv","id":"2011.06507","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with Videos: Combining Offline Observations with Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Karl Schmeckpeper, Kostas Daniilidis, Oleh Rybkin, Sergey Levine","submitted_at":"2020-11-12T17:15:48Z","abstract_excerpt":"Reinforcement learning is a powerful framework for robots to acquire skills from experience, but often requires a substantial amount of online data collection. As a result, it is difficult to collect sufficiently diverse experiences that are needed for robots to generalize broadly. Videos of humans, on the other hand, are a readily available source of broad and interesting experiences. In this paper, we consider the question: can we perform reinforcement learning directly on experience collected by humans? This problem is particularly difficult, as such videos are not annotated with actions an"},"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":"2011.06507","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-12T17:15:48Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"f46356e47934f592824e106e80d5ad04b811fc41c598389690e72bc4013e7343","abstract_canon_sha256":"4ced5af5ecc59abe8a126d2a22fcf8e512356ae959373756b5b4ba813e7ab7fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:14.538101Z","signature_b64":"3CG9LNMxzDhb4hbYI8ky/eA4+vBBX7elUyBja2SqR7g82OH0K28AtB1z/sQYiaSvDUROEWx46U5jeEVPWVQuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ea4a3923c0b8bc1e1adc4e9a368e4a07e190fc1359f217048fae4a92784ca37","last_reissued_at":"2026-07-05T03:29:14.537715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:14.537715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Videos: Combining Offline Observations with Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Karl Schmeckpeper, Kostas Daniilidis, Oleh Rybkin, Sergey Levine","submitted_at":"2020-11-12T17:15:48Z","abstract_excerpt":"Reinforcement learning is a powerful framework for robots to acquire skills from experience, but often requires a substantial amount of online data collection. As a result, it is difficult to collect sufficiently diverse experiences that are needed for robots to generalize broadly. Videos of humans, on the other hand, are a readily available source of broad and interesting experiences. In this paper, we consider the question: can we perform reinforcement learning directly on experience collected by humans? This problem is particularly difficult, as such videos are not annotated with actions an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06507","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/2011.06507/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":"2011.06507","created_at":"2026-07-05T03:29:14.537774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.06507v2","created_at":"2026-07-05T03:29:14.537774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06507","created_at":"2026-07-05T03:29:14.537774+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2SKHER4BOF4","created_at":"2026-07-05T03:29:14.537774+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2SKHER4BOF4DYNN","created_at":"2026-07-05T03:29:14.537774+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2SKHER4","created_at":"2026-07-05T03:29:14.537774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03201","citing_title":"Reinforcement Learning from Cross-domain Videos with Video Prediction Model","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14057","citing_title":"Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2310.06114","citing_title":"Learning Interactive Real-World Simulators","ref_index":208,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14057","citing_title":"Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2210.00030","citing_title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04502","citing_title":"Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F2SKHER4BOF4DYNNYTU2G2HEUB","json":"https://pith.science/pith/F2SKHER4BOF4DYNNYTU2G2HEUB.json","graph_json":"https://pith.science/api/pith-number/F2SKHER4BOF4DYNNYTU2G2HEUB/graph.json","events_json":"https://pith.science/api/pith-number/F2SKHER4BOF4DYNNYTU2G2HEUB/events.json","paper":"https://pith.science/paper/F2SKHER4"},"agent_actions":{"view_html":"https://pith.science/pith/F2SKHER4BOF4DYNNYTU2G2HEUB","download_json":"https://pith.science/pith/F2SKHER4BOF4DYNNYTU2G2HEUB.json","view_paper":"https://pith.science/paper/F2SKHER4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.06507&json=true","fetch_graph":"https://pith.science/api/pith-number/F2SKHER4BOF4DYNNYTU2G2HEUB/graph.json","fetch_events":"https://pith.science/api/pith-number/F2SKHER4BOF4DYNNYTU2G2HEUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2SKHER4BOF4DYNNYTU2G2HEUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2SKHER4BOF4DYNNYTU2G2HEUB/action/storage_attestation","attest_author":"https://pith.science/pith/F2SKHER4BOF4DYNNYTU2G2HEUB/action/author_attestation","sign_citation":"https://pith.science/pith/F2SKHER4BOF4DYNNYTU2G2HEUB/action/citation_signature","submit_replication":"https://pith.science/pith/F2SKHER4BOF4DYNNYTU2G2HEUB/action/replication_record"}},"created_at":"2026-07-05T03:29:14.537774+00:00","updated_at":"2026-07-05T03:29:14.537774+00:00"}