{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XB5ZKLH34P57ZB7ZJJ272A6345","short_pith_number":"pith:XB5ZKLH3","schema_version":"1.0","canonical_sha256":"b87b952cfbe3fbfc87f94a75fd03dbe7582267c22ee03af9643e99277a837b25","source":{"kind":"arxiv","id":"2011.04741","version":2},"attestation_state":"computed","paper":{"title":"Learning Task Space Actions for Bipedal Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alan Fern, Helei Duan, Jeremy Dao, Jonathan Hurst, Kevin Green, Taylor Apgar","submitted_at":"2020-11-09T20:35:33Z","abstract_excerpt":"Recent work has demonstrated the success of reinforcement learning (RL) for training bipedal locomotion policies for real robots. This prior work, however, has focused on learning joint-coordination controllers based on an objective of following joint trajectories produced by already available controllers. As such, it is difficult to train these approaches to achieve higher-level goals of legged locomotion, such as simply specifying the desired end-effector foot movement or ground reaction forces. In this work, we propose an approach for integrating knowledge of the robot system into RL to all"},"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":"2011.04741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-09T20:35:33Z","cross_cats_sorted":[],"title_canon_sha256":"dba64348cd9512b54807a7d8426f31f27250dd653f86b1a64a4ad3cad862a8d2","abstract_canon_sha256":"39926a613abef2690410bb50bc59b4631a40897c01e3e0cbb4302c7d1cea2e65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:56.807804Z","signature_b64":"xLqUqI7a3A1N+WR8BxVIyipm7dXUXKYF4e4cGC3pytuWAl2gktW6xXQIDLJfeIn+Ye3yHTCekk202ScUz9IWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b87b952cfbe3fbfc87f94a75fd03dbe7582267c22ee03af9643e99277a837b25","last_reissued_at":"2026-07-05T02:37:56.807332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:56.807332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Task Space Actions for Bipedal Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alan Fern, Helei Duan, Jeremy Dao, Jonathan Hurst, Kevin Green, Taylor Apgar","submitted_at":"2020-11-09T20:35:33Z","abstract_excerpt":"Recent work has demonstrated the success of reinforcement learning (RL) for training bipedal locomotion policies for real robots. This prior work, however, has focused on learning joint-coordination controllers based on an objective of following joint trajectories produced by already available controllers. As such, it is difficult to train these approaches to achieve higher-level goals of legged locomotion, such as simply specifying the desired end-effector foot movement or ground reaction forces. In this work, we propose an approach for integrating knowledge of the robot system into RL to all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04741","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/2011.04741/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":"2011.04741","created_at":"2026-07-05T02:37:56.807393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.04741v2","created_at":"2026-07-05T02:37:56.807393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04741","created_at":"2026-07-05T02:37:56.807393+00:00"},{"alias_kind":"pith_short_12","alias_value":"XB5ZKLH34P57","created_at":"2026-07-05T02:37:56.807393+00:00"},{"alias_kind":"pith_short_16","alias_value":"XB5ZKLH34P57ZB7Z","created_at":"2026-07-05T02:37:56.807393+00:00"},{"alias_kind":"pith_short_8","alias_value":"XB5ZKLH3","created_at":"2026-07-05T02:37:56.807393+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/XB5ZKLH34P57ZB7ZJJ272A6345","json":"https://pith.science/pith/XB5ZKLH34P57ZB7ZJJ272A6345.json","graph_json":"https://pith.science/api/pith-number/XB5ZKLH34P57ZB7ZJJ272A6345/graph.json","events_json":"https://pith.science/api/pith-number/XB5ZKLH34P57ZB7ZJJ272A6345/events.json","paper":"https://pith.science/paper/XB5ZKLH3"},"agent_actions":{"view_html":"https://pith.science/pith/XB5ZKLH34P57ZB7ZJJ272A6345","download_json":"https://pith.science/pith/XB5ZKLH34P57ZB7ZJJ272A6345.json","view_paper":"https://pith.science/paper/XB5ZKLH3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.04741&json=true","fetch_graph":"https://pith.science/api/pith-number/XB5ZKLH34P57ZB7ZJJ272A6345/graph.json","fetch_events":"https://pith.science/api/pith-number/XB5ZKLH34P57ZB7ZJJ272A6345/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XB5ZKLH34P57ZB7ZJJ272A6345/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XB5ZKLH34P57ZB7ZJJ272A6345/action/storage_attestation","attest_author":"https://pith.science/pith/XB5ZKLH34P57ZB7ZJJ272A6345/action/author_attestation","sign_citation":"https://pith.science/pith/XB5ZKLH34P57ZB7ZJJ272A6345/action/citation_signature","submit_replication":"https://pith.science/pith/XB5ZKLH34P57ZB7ZJJ272A6345/action/replication_record"}},"created_at":"2026-07-05T02:37:56.807393+00:00","updated_at":"2026-07-05T02:37:56.807393+00:00"}