{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BUNORPAJ3B6XJTI6X4DTJEE6ET","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":"1d97650cde324aa09dc27b242abefc73bba7e597df9b2ce31e73712928ed1cbb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-02-20T03:36:39Z","title_canon_sha256":"441350bfde98ed00e6d74cb43d4cd3cf300a8b44266466d5c9ea27fc1318e051"},"schema_version":"1.0","source":{"id":"2002.08550","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.08550","created_at":"2026-07-05T01:48:25Z"},{"alias_kind":"arxiv_version","alias_value":"2002.08550v3","created_at":"2026-07-05T01:48:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.08550","created_at":"2026-07-05T01:48:25Z"},{"alias_kind":"pith_short_12","alias_value":"BUNORPAJ3B6X","created_at":"2026-07-05T01:48:25Z"},{"alias_kind":"pith_short_16","alias_value":"BUNORPAJ3B6XJTI6","created_at":"2026-07-05T01:48:25Z"},{"alias_kind":"pith_short_8","alias_value":"BUNORPAJ","created_at":"2026-07-05T01:48:25Z"}],"graph_snapshots":[{"event_id":"sha256:665013ac7cee34e04f46a5a5b5e0facffd9f698d7391f199bf296a87efa36309","target":"graph","created_at":"2026-07-05T01:48:25Z","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/2002.08550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reliable and stable locomotion has been one of the most fundamental challenges for legged robots. Deep reinforcement learning (deep RL) has emerged as a promising method for developing such control policies autonomously. In this paper, we develop a system for learning legged locomotion policies with deep RL in the real world with minimal human effort. The key difficulties for on-robot learning systems are automatic data collection and safety. We overcome these two challenges by developing a multi-task learning procedure and a safety-constrained RL framework. We tested our system on the task of","authors_text":"Jie Tan, Peng Xu, Sehoon Ha, Sergey Levine, Zhenyu Tan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-02-20T03:36:39Z","title":"Learning to Walk in the Real World with Minimal Human Effort"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.08550","kind":"arxiv","version":3},"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":"sha256:033b5f46159a84ed7e185b64c409a81237b1269f31fb91f033979f88a9e21f7f","target":"record","created_at":"2026-07-05T01:48:25Z","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":"1d97650cde324aa09dc27b242abefc73bba7e597df9b2ce31e73712928ed1cbb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-02-20T03:36:39Z","title_canon_sha256":"441350bfde98ed00e6d74cb43d4cd3cf300a8b44266466d5c9ea27fc1318e051"},"schema_version":"1.0","source":{"id":"2002.08550","kind":"arxiv","version":3}},"canonical_sha256":"0d1ae8bc09d87d74cd1ebf0734909e24c05c54347b71bab2fcca4156702f87b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d1ae8bc09d87d74cd1ebf0734909e24c05c54347b71bab2fcca4156702f87b7","first_computed_at":"2026-07-05T01:48:25.894349Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:48:25.894349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RWpUQyT9ltV2FH/BXh+zZ6cgexADT9XPcAHvNtqIyJhoXt9zqdNYTYAKACKO5P2b0lek77YjeqzFVdavFaviDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:48:25.894786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.08550","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:033b5f46159a84ed7e185b64c409a81237b1269f31fb91f033979f88a9e21f7f","sha256:665013ac7cee34e04f46a5a5b5e0facffd9f698d7391f199bf296a87efa36309"],"state_sha256":"140df26e7ce10b485af446b1a27f4522460e39e781141b7eb56b79d4a188bdcc"}