{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2Y4ZQ3VNR2PMKC7UGNYV63HEUV","short_pith_number":"pith:2Y4ZQ3VN","schema_version":"1.0","canonical_sha256":"d639986ead8e9ec50bf433715f6ce4a5683ab77dbdd1a790a77ac242e332902c","source":{"kind":"arxiv","id":"2011.05513","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Terrain Generalization for Visual Locomotion Policies","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alejandro Escontrela, Atil Iscen, George Yu, Jie Tan, Peng Xu","submitted_at":"2020-11-11T02:10:48Z","abstract_excerpt":"Legged robots have unparalleled mobility on unstructured terrains. However, it remains an open challenge to design locomotion controllers that can operate in a large variety of environments. In this paper, we address this challenge of automatically learning locomotion controllers that can generalize to a diverse collection of terrains often encountered in the real world. We frame this challenge as a multi-task reinforcement learning problem and define each task as a type of terrain that the robot needs to traverse. We propose an end-to-end learning approach that makes direct use of the raw ext"},"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":"2011.05513","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2020-11-11T02:10:48Z","cross_cats_sorted":[],"title_canon_sha256":"cbddfa38345f5f3045f8e1bf7d52fd3cb183c5efd78d2d7840cb3bb2adc025bd","abstract_canon_sha256":"0bb666763409e55a4289ca51905602a9c7eba4a0cc70860df9f6d43685ef8b48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:50.769531Z","signature_b64":"n1jTY6Z3q2chhB++UorJFmNj7vlj/50VA9WXwmnK8jdxTK5tpSs+vnxxJNg0fHLJnRqFhmYf2hQtEaAqlASDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d639986ead8e9ec50bf433715f6ce4a5683ab77dbdd1a790a77ac242e332902c","last_reissued_at":"2026-07-05T01:50:50.769130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:50.769130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Terrain Generalization for Visual Locomotion Policies","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alejandro Escontrela, Atil Iscen, George Yu, Jie Tan, Peng Xu","submitted_at":"2020-11-11T02:10:48Z","abstract_excerpt":"Legged robots have unparalleled mobility on unstructured terrains. However, it remains an open challenge to design locomotion controllers that can operate in a large variety of environments. In this paper, we address this challenge of automatically learning locomotion controllers that can generalize to a diverse collection of terrains often encountered in the real world. We frame this challenge as a multi-task reinforcement learning problem and define each task as a type of terrain that the robot needs to traverse. We propose an end-to-end learning approach that makes direct use of the raw ext"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05513","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/2011.05513/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":"2011.05513","created_at":"2026-07-05T01:50:50.769185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.05513v1","created_at":"2026-07-05T01:50:50.769185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05513","created_at":"2026-07-05T01:50:50.769185+00:00"},{"alias_kind":"pith_short_12","alias_value":"2Y4ZQ3VNR2PM","created_at":"2026-07-05T01:50:50.769185+00:00"},{"alias_kind":"pith_short_16","alias_value":"2Y4ZQ3VNR2PMKC7U","created_at":"2026-07-05T01:50:50.769185+00:00"},{"alias_kind":"pith_short_8","alias_value":"2Y4ZQ3VN","created_at":"2026-07-05T01:50:50.769185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20036","citing_title":"Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped Locomotion","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2Y4ZQ3VNR2PMKC7UGNYV63HEUV","json":"https://pith.science/pith/2Y4ZQ3VNR2PMKC7UGNYV63HEUV.json","graph_json":"https://pith.science/api/pith-number/2Y4ZQ3VNR2PMKC7UGNYV63HEUV/graph.json","events_json":"https://pith.science/api/pith-number/2Y4ZQ3VNR2PMKC7UGNYV63HEUV/events.json","paper":"https://pith.science/paper/2Y4ZQ3VN"},"agent_actions":{"view_html":"https://pith.science/pith/2Y4ZQ3VNR2PMKC7UGNYV63HEUV","download_json":"https://pith.science/pith/2Y4ZQ3VNR2PMKC7UGNYV63HEUV.json","view_paper":"https://pith.science/paper/2Y4ZQ3VN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.05513&json=true","fetch_graph":"https://pith.science/api/pith-number/2Y4ZQ3VNR2PMKC7UGNYV63HEUV/graph.json","fetch_events":"https://pith.science/api/pith-number/2Y4ZQ3VNR2PMKC7UGNYV63HEUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2Y4ZQ3VNR2PMKC7UGNYV63HEUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2Y4ZQ3VNR2PMKC7UGNYV63HEUV/action/storage_attestation","attest_author":"https://pith.science/pith/2Y4ZQ3VNR2PMKC7UGNYV63HEUV/action/author_attestation","sign_citation":"https://pith.science/pith/2Y4ZQ3VNR2PMKC7UGNYV63HEUV/action/citation_signature","submit_replication":"https://pith.science/pith/2Y4ZQ3VNR2PMKC7UGNYV63HEUV/action/replication_record"}},"created_at":"2026-07-05T01:50:50.769185+00:00","updated_at":"2026-07-05T01:50:50.769185+00:00"}