{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CW55YGOWJUP63ZJVEDXKK5ZPAF","short_pith_number":"pith:CW55YGOW","schema_version":"1.0","canonical_sha256":"15bbdc19d64d1fede53520eea5772f014f8365fbd6df7131904397fa81b1c896","source":{"kind":"arxiv","id":"2401.16889","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Glen Berseth, Koushil Sreenath, Pieter Abbeel, Sergey Levine, Xue Bin Peng, Zhongyu Li","submitted_at":"2024-01-30T10:48:43Z","abstract_excerpt":"This paper presents a comprehensive study on using deep reinforcement learning (RL) to create dynamic locomotion controllers for bipedal robots. Going beyond focusing on a single locomotion skill, we develop a general control solution that can be used for a range of dynamic bipedal skills, from periodic walking and running to aperiodic jumping and standing. Our RL-based controller incorporates a novel dual-history architecture, utilizing both a long-term and short-term input/output (I/O) history of the robot. This control architecture, when trained through the proposed end-to-end RL approach, "},"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":"2401.16889","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-01-30T10:48:43Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"43a5160e27b80ded618ad33da0400aae60113eaaab75a07fb2e8b028ed4ed33f","abstract_canon_sha256":"5c6137c5ce110e54a4b70e5cc8a44bcfdec0e7b8ac545705ceebf8306979b7e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:05.509941Z","signature_b64":"E6dkhROlSD9F21EAPP4qnGVEA3q+fRwzC1K2WtLfbU9iLGfquVs7TxISNpLHIOL3SGG/zt0GQDbHm6PXgJb6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15bbdc19d64d1fede53520eea5772f014f8365fbd6df7131904397fa81b1c896","last_reissued_at":"2026-07-05T08:59:05.509481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:05.509481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Glen Berseth, Koushil Sreenath, Pieter Abbeel, Sergey Levine, Xue Bin Peng, Zhongyu Li","submitted_at":"2024-01-30T10:48:43Z","abstract_excerpt":"This paper presents a comprehensive study on using deep reinforcement learning (RL) to create dynamic locomotion controllers for bipedal robots. Going beyond focusing on a single locomotion skill, we develop a general control solution that can be used for a range of dynamic bipedal skills, from periodic walking and running to aperiodic jumping and standing. Our RL-based controller incorporates a novel dual-history architecture, utilizing both a long-term and short-term input/output (I/O) history of the robot. This control architecture, when trained through the proposed end-to-end RL approach, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16889","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/2401.16889/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":"2401.16889","created_at":"2026-07-05T08:59:05.509533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16889v2","created_at":"2026-07-05T08:59:05.509533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16889","created_at":"2026-07-05T08:59:05.509533+00:00"},{"alias_kind":"pith_short_12","alias_value":"CW55YGOWJUP6","created_at":"2026-07-05T08:59:05.509533+00:00"},{"alias_kind":"pith_short_16","alias_value":"CW55YGOWJUP63ZJV","created_at":"2026-07-05T08:59:05.509533+00:00"},{"alias_kind":"pith_short_8","alias_value":"CW55YGOW","created_at":"2026-07-05T08:59:05.509533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24592","citing_title":"MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02636","citing_title":"Too Much of a Good Thing: When sim2real Efforts Impede Policy Learning (And What to Do About It)","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2408.07295","citing_title":"Learning Multi-Modal Whole-Body Control for Real-World Humanoid Robots","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12909","citing_title":"Tree Learning: A Multi-Skill Continual Learning Framework for Humanoid Robots","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CW55YGOWJUP63ZJVEDXKK5ZPAF","json":"https://pith.science/pith/CW55YGOWJUP63ZJVEDXKK5ZPAF.json","graph_json":"https://pith.science/api/pith-number/CW55YGOWJUP63ZJVEDXKK5ZPAF/graph.json","events_json":"https://pith.science/api/pith-number/CW55YGOWJUP63ZJVEDXKK5ZPAF/events.json","paper":"https://pith.science/paper/CW55YGOW"},"agent_actions":{"view_html":"https://pith.science/pith/CW55YGOWJUP63ZJVEDXKK5ZPAF","download_json":"https://pith.science/pith/CW55YGOWJUP63ZJVEDXKK5ZPAF.json","view_paper":"https://pith.science/paper/CW55YGOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16889&json=true","fetch_graph":"https://pith.science/api/pith-number/CW55YGOWJUP63ZJVEDXKK5ZPAF/graph.json","fetch_events":"https://pith.science/api/pith-number/CW55YGOWJUP63ZJVEDXKK5ZPAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CW55YGOWJUP63ZJVEDXKK5ZPAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CW55YGOWJUP63ZJVEDXKK5ZPAF/action/storage_attestation","attest_author":"https://pith.science/pith/CW55YGOWJUP63ZJVEDXKK5ZPAF/action/author_attestation","sign_citation":"https://pith.science/pith/CW55YGOWJUP63ZJVEDXKK5ZPAF/action/citation_signature","submit_replication":"https://pith.science/pith/CW55YGOWJUP63ZJVEDXKK5ZPAF/action/replication_record"}},"created_at":"2026-07-05T08:59:05.509533+00:00","updated_at":"2026-07-05T08:59:05.509533+00:00"}