{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UTOXFSVYZPY3L35LRPVRLQKBGS","short_pith_number":"pith:UTOXFSVY","schema_version":"1.0","canonical_sha256":"a4dd72cab8cbf1b5efab8beb15c1413483d485b2a0d11bb111eb6ce9d98fc3c3","source":{"kind":"arxiv","id":"1907.03613","version":2},"attestation_state":"computed","paper":{"title":"Data Efficient Reinforcement Learning for Legged Robots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Atil Iscen, Jie Tan, Ken Caluwaerts, Tingnan Zhang, Vikas Sindhwani, Yuxiang Yang","submitted_at":"2019-07-08T13:43:06Z","abstract_excerpt":"We present a model-based framework for robot locomotion that achieves walking based on only 4.5 minutes (45,000 control steps) of data collected on a quadruped robot. To accurately model the robot's dynamics over a long horizon, we introduce a loss function that tracks the model's prediction over multiple timesteps. We adapt model predictive control to account for planning latency, which allows the learned model to be used for real time control. Additionally, to ensure safe exploration during model learning, we embed prior knowledge of leg trajectories into the action space. The resulting syst"},"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":"1907.03613","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-08T13:43:06Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"71ab4ea992de53273aac873122d6b326ca1f26896c263cd5eda9db41a30a0203","abstract_canon_sha256":"049d7a281f16ac5ab81ff27ac19e8870e03d7e3b773bf37e2121b9158312d127"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:02.691112Z","signature_b64":"6Mc7GGU2567PVKuAGbZjsOQa9kPUTEJvhMKeYNPpJUNJwk+CXCNijxbTYYRYFu9zb7hCokifNRGxwVYs8EcIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4dd72cab8cbf1b5efab8beb15c1413483d485b2a0d11bb111eb6ce9d98fc3c3","last_reissued_at":"2026-07-05T00:10:02.690664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:02.690664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Efficient Reinforcement Learning for Legged Robots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Atil Iscen, Jie Tan, Ken Caluwaerts, Tingnan Zhang, Vikas Sindhwani, Yuxiang Yang","submitted_at":"2019-07-08T13:43:06Z","abstract_excerpt":"We present a model-based framework for robot locomotion that achieves walking based on only 4.5 minutes (45,000 control steps) of data collected on a quadruped robot. To accurately model the robot's dynamics over a long horizon, we introduce a loss function that tracks the model's prediction over multiple timesteps. We adapt model predictive control to account for planning latency, which allows the learned model to be used for real time control. Additionally, to ensure safe exploration during model learning, we embed prior knowledge of leg trajectories into the action space. The resulting syst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03613","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/1907.03613/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":"1907.03613","created_at":"2026-07-05T00:10:02.690722+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.03613v2","created_at":"2026-07-05T00:10:02.690722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03613","created_at":"2026-07-05T00:10:02.690722+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTOXFSVYZPY3","created_at":"2026-07-05T00:10:02.690722+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTOXFSVYZPY3L35L","created_at":"2026-07-05T00:10:02.690722+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTOXFSVY","created_at":"2026-07-05T00:10:02.690722+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03978","citing_title":"Stochastic Multiple Shooting Trajectory Optimization via Sequential Local Policy Evaluation","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UTOXFSVYZPY3L35LRPVRLQKBGS","json":"https://pith.science/pith/UTOXFSVYZPY3L35LRPVRLQKBGS.json","graph_json":"https://pith.science/api/pith-number/UTOXFSVYZPY3L35LRPVRLQKBGS/graph.json","events_json":"https://pith.science/api/pith-number/UTOXFSVYZPY3L35LRPVRLQKBGS/events.json","paper":"https://pith.science/paper/UTOXFSVY"},"agent_actions":{"view_html":"https://pith.science/pith/UTOXFSVYZPY3L35LRPVRLQKBGS","download_json":"https://pith.science/pith/UTOXFSVYZPY3L35LRPVRLQKBGS.json","view_paper":"https://pith.science/paper/UTOXFSVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.03613&json=true","fetch_graph":"https://pith.science/api/pith-number/UTOXFSVYZPY3L35LRPVRLQKBGS/graph.json","fetch_events":"https://pith.science/api/pith-number/UTOXFSVYZPY3L35LRPVRLQKBGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTOXFSVYZPY3L35LRPVRLQKBGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTOXFSVYZPY3L35LRPVRLQKBGS/action/storage_attestation","attest_author":"https://pith.science/pith/UTOXFSVYZPY3L35LRPVRLQKBGS/action/author_attestation","sign_citation":"https://pith.science/pith/UTOXFSVYZPY3L35LRPVRLQKBGS/action/citation_signature","submit_replication":"https://pith.science/pith/UTOXFSVYZPY3L35LRPVRLQKBGS/action/replication_record"}},"created_at":"2026-07-05T00:10:02.690722+00:00","updated_at":"2026-07-05T00:10:02.690722+00:00"}