{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WDDI2EKZ5UHCI44F7DA23NAWNL","short_pith_number":"pith:WDDI2EKZ","schema_version":"1.0","canonical_sha256":"b0c68d1159ed0e247385f8c1adb4166ad4a35e5376858e7dc26c8e2d32b39c1a","source":{"kind":"arxiv","id":"2103.14295","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots","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":"Glen Berseth, Koushil Sreenath, Pieter Abbeel, Sergey Levine, Xue Bin Peng, Xuxin Cheng, Zhongyu Li","submitted_at":"2021-03-26T07:14:01Z","abstract_excerpt":"Developing robust walking controllers for bipedal robots is a challenging endeavor. Traditional model-based locomotion controllers require simplifying assumptions and careful modelling; any small errors can result in unstable control. To address these challenges for bipedal locomotion, we present a model-free reinforcement learning framework for training robust locomotion policies in simulation, which can then be transferred to a real bipedal Cassie robot. To facilitate sim-to-real transfer, domain randomization is used to encourage the policies to learn behaviors that are robust across variat"},"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":"2103.14295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-03-26T07:14:01Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"14da9c075d0197d4e01075a8d1f9586ed8d5c607e45fcc485d53d3df9eafe598","abstract_canon_sha256":"2ee317e208660c37d84a80a8a02cd61c9137b2f2abe4afc74f1addeec771dfe1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:32.563397Z","signature_b64":"1r3CwTewFpN5/ATASmoRTdhNtdWjGUPL0LSvtwhiq7jd2MFBK8QXwqfd7dgBtRA2NqEy38HwDij0J7B98PwHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0c68d1159ed0e247385f8c1adb4166ad4a35e5376858e7dc26c8e2d32b39c1a","last_reissued_at":"2026-07-05T02:26:32.562917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:32.562917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots","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":"Glen Berseth, Koushil Sreenath, Pieter Abbeel, Sergey Levine, Xue Bin Peng, Xuxin Cheng, Zhongyu Li","submitted_at":"2021-03-26T07:14:01Z","abstract_excerpt":"Developing robust walking controllers for bipedal robots is a challenging endeavor. Traditional model-based locomotion controllers require simplifying assumptions and careful modelling; any small errors can result in unstable control. To address these challenges for bipedal locomotion, we present a model-free reinforcement learning framework for training robust locomotion policies in simulation, which can then be transferred to a real bipedal Cassie robot. To facilitate sim-to-real transfer, domain randomization is used to encourage the policies to learn behaviors that are robust across variat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14295","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/2103.14295/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":"2103.14295","created_at":"2026-07-05T02:26:32.562973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.14295v1","created_at":"2026-07-05T02:26:32.562973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14295","created_at":"2026-07-05T02:26:32.562973+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDDI2EKZ5UHC","created_at":"2026-07-05T02:26:32.562973+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDDI2EKZ5UHCI44F","created_at":"2026-07-05T02:26:32.562973+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDDI2EKZ","created_at":"2026-07-05T02:26:32.562973+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/WDDI2EKZ5UHCI44F7DA23NAWNL","json":"https://pith.science/pith/WDDI2EKZ5UHCI44F7DA23NAWNL.json","graph_json":"https://pith.science/api/pith-number/WDDI2EKZ5UHCI44F7DA23NAWNL/graph.json","events_json":"https://pith.science/api/pith-number/WDDI2EKZ5UHCI44F7DA23NAWNL/events.json","paper":"https://pith.science/paper/WDDI2EKZ"},"agent_actions":{"view_html":"https://pith.science/pith/WDDI2EKZ5UHCI44F7DA23NAWNL","download_json":"https://pith.science/pith/WDDI2EKZ5UHCI44F7DA23NAWNL.json","view_paper":"https://pith.science/paper/WDDI2EKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.14295&json=true","fetch_graph":"https://pith.science/api/pith-number/WDDI2EKZ5UHCI44F7DA23NAWNL/graph.json","fetch_events":"https://pith.science/api/pith-number/WDDI2EKZ5UHCI44F7DA23NAWNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDDI2EKZ5UHCI44F7DA23NAWNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDDI2EKZ5UHCI44F7DA23NAWNL/action/storage_attestation","attest_author":"https://pith.science/pith/WDDI2EKZ5UHCI44F7DA23NAWNL/action/author_attestation","sign_citation":"https://pith.science/pith/WDDI2EKZ5UHCI44F7DA23NAWNL/action/citation_signature","submit_replication":"https://pith.science/pith/WDDI2EKZ5UHCI44F7DA23NAWNL/action/replication_record"}},"created_at":"2026-07-05T02:26:32.562973+00:00","updated_at":"2026-07-05T02:26:32.562973+00:00"}