{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XB5ZKLH34P57ZB7ZJJ272A6345","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"39926a613abef2690410bb50bc59b4631a40897c01e3e0cbb4302c7d1cea2e65","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-09T20:35:33Z","title_canon_sha256":"dba64348cd9512b54807a7d8426f31f27250dd653f86b1a64a4ad3cad862a8d2"},"schema_version":"1.0","source":{"id":"2011.04741","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.04741","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"arxiv_version","alias_value":"2011.04741v2","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04741","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_12","alias_value":"XB5ZKLH34P57","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_16","alias_value":"XB5ZKLH34P57ZB7Z","created_at":"2026-07-05T02:37:56Z"},{"alias_kind":"pith_short_8","alias_value":"XB5ZKLH3","created_at":"2026-07-05T02:37:56Z"}],"graph_snapshots":[{"event_id":"sha256:76dbdf90672998d5836d797d1b702b890e2bbccda9d49972284ab03f2fa17d68","target":"graph","created_at":"2026-07-05T02:37:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.04741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alan Fern, Helei Duan, Jeremy Dao, Jonathan Hurst, Kevin Green, Taylor Apgar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-09T20:35:33Z","title":"Learning Task Space Actions for Bipedal Locomotion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04741","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:db4b49e935c39b74ecff2b3b272b26d513efbc104cce157c2625afb350fe6992","target":"record","created_at":"2026-07-05T02:37:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"39926a613abef2690410bb50bc59b4631a40897c01e3e0cbb4302c7d1cea2e65","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-09T20:35:33Z","title_canon_sha256":"dba64348cd9512b54807a7d8426f31f27250dd653f86b1a64a4ad3cad862a8d2"},"schema_version":"1.0","source":{"id":"2011.04741","kind":"arxiv","version":2}},"canonical_sha256":"b87b952cfbe3fbfc87f94a75fd03dbe7582267c22ee03af9643e99277a837b25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b87b952cfbe3fbfc87f94a75fd03dbe7582267c22ee03af9643e99277a837b25","first_computed_at":"2026-07-05T02:37:56.807332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:37:56.807332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xLqUqI7a3A1N+WR8BxVIyipm7dXUXKYF4e4cGC3pytuWAl2gktW6xXQIDLJfeIn+Ye3yHTCekk202ScUz9IWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:37:56.807804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.04741","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db4b49e935c39b74ecff2b3b272b26d513efbc104cce157c2625afb350fe6992","sha256:76dbdf90672998d5836d797d1b702b890e2bbccda9d49972284ab03f2fa17d68"],"state_sha256":"409ca29489fe4ba0c92fc4ef5069e3182114fc7a407619171b73a6989f8b8346"}