{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KIHZ644YIQ62SHAECXCTZDZQ3P","short_pith_number":"pith:KIHZ644Y","canonical_record":{"source":{"id":"2011.05541","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2020-11-11T04:38:52Z","cross_cats_sorted":[],"title_canon_sha256":"8f1808845881397d9ca10e7184bc37b56eff7c7cd0deb834f6870c56837cc5a9","abstract_canon_sha256":"9e6c4f0ac640ddc2c27716651a41bff0e5566f4324670366958fb396a587e59f"},"schema_version":"1.0"},"canonical_sha256":"520f9f7398443da91c0415c53c8f30dbfaf7873bcaaa3ea8ec6f808f2d80179b","source":{"kind":"arxiv","id":"2011.05541","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.05541","created_at":"2026-07-05T01:50:51Z"},{"alias_kind":"arxiv_version","alias_value":"2011.05541v1","created_at":"2026-07-05T01:50:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05541","created_at":"2026-07-05T01:50:51Z"},{"alias_kind":"pith_short_12","alias_value":"KIHZ644YIQ62","created_at":"2026-07-05T01:50:51Z"},{"alias_kind":"pith_short_16","alias_value":"KIHZ644YIQ62SHAE","created_at":"2026-07-05T01:50:51Z"},{"alias_kind":"pith_short_8","alias_value":"KIHZ644Y","created_at":"2026-07-05T01:50:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KIHZ644YIQ62SHAECXCTZDZQ3P","target":"record","payload":{"canonical_record":{"source":{"id":"2011.05541","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2020-11-11T04:38:52Z","cross_cats_sorted":[],"title_canon_sha256":"8f1808845881397d9ca10e7184bc37b56eff7c7cd0deb834f6870c56837cc5a9","abstract_canon_sha256":"9e6c4f0ac640ddc2c27716651a41bff0e5566f4324670366958fb396a587e59f"},"schema_version":"1.0"},"canonical_sha256":"520f9f7398443da91c0415c53c8f30dbfaf7873bcaaa3ea8ec6f808f2d80179b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:51.066287Z","signature_b64":"4tG75rrcblPPMJ36Zg8SyHfxqimiBFLA3rXevtXPLwAXEVvm0sPmbFzlqPGjtMHlFjw9Fm8c5OvHOsxiO852BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"520f9f7398443da91c0415c53c8f30dbfaf7873bcaaa3ea8ec6f808f2d80179b","last_reissued_at":"2026-07-05T01:50:51.065765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:51.065765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.05541","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:50:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dUBEtLlA9Pb+EdtVjbNDvTC0pAswtY3K0yS/6fUhGiCqrlne75hbCBiFi59jdIgDiK1v4C4nBQXXxbybF272Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:52:04.305669Z"},"content_sha256":"429d2ea43bc58758bcb9f97f6f6c68768ce93954a88c7a8686139c5637aa7dc8","schema_version":"1.0","event_id":"sha256:429d2ea43bc58758bcb9f97f6f6c68768ce93954a88c7a8686139c5637aa7dc8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KIHZ644YIQ62SHAECXCTZDZQ3P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Agile Locomotion Skills with a Mentor","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alejandro Escontrela, Atil Iscen, Deepali Jain, George Yu, Jie Tan, Ken Caluwaerts","submitted_at":"2020-11-11T04:38:52Z","abstract_excerpt":"Developing agile behaviors for legged robots remains a challenging problem. While deep reinforcement learning is a promising approach, learning truly agile behaviors typically requires tedious reward shaping and careful curriculum design. We formulate agile locomotion as a multi-stage learning problem in which a mentor guides the agent throughout the training. The mentor is optimized to place a checkpoint to guide the movement of the robot's center of mass while the student (i.e. the robot) learns to reach these checkpoints. Once the student can solve the task, we teach the student to perform "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05541","kind":"arxiv","version":1},"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/2011.05541/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:50:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wdike7UBFLdqGxvetuqAaT9NAle+BS6HzgmRhFSQzz1zQ+lUtx3+DaGLfchx++Cejy56jENeXdybHevNs0NUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:52:04.306210Z"},"content_sha256":"69b873a2ebe7edc22545e457cc210688e11794719aec24b9ee5fa65573427045","schema_version":"1.0","event_id":"sha256:69b873a2ebe7edc22545e457cc210688e11794719aec24b9ee5fa65573427045"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KIHZ644YIQ62SHAECXCTZDZQ3P/bundle.json","state_url":"https://pith.science/pith/KIHZ644YIQ62SHAECXCTZDZQ3P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KIHZ644YIQ62SHAECXCTZDZQ3P/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-31T17:52:04Z","links":{"resolver":"https://pith.science/pith/KIHZ644YIQ62SHAECXCTZDZQ3P","bundle":"https://pith.science/pith/KIHZ644YIQ62SHAECXCTZDZQ3P/bundle.json","state":"https://pith.science/pith/KIHZ644YIQ62SHAECXCTZDZQ3P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KIHZ644YIQ62SHAECXCTZDZQ3P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KIHZ644YIQ62SHAECXCTZDZQ3P","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":"9e6c4f0ac640ddc2c27716651a41bff0e5566f4324670366958fb396a587e59f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2020-11-11T04:38:52Z","title_canon_sha256":"8f1808845881397d9ca10e7184bc37b56eff7c7cd0deb834f6870c56837cc5a9"},"schema_version":"1.0","source":{"id":"2011.05541","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.05541","created_at":"2026-07-05T01:50:51Z"},{"alias_kind":"arxiv_version","alias_value":"2011.05541v1","created_at":"2026-07-05T01:50:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05541","created_at":"2026-07-05T01:50:51Z"},{"alias_kind":"pith_short_12","alias_value":"KIHZ644YIQ62","created_at":"2026-07-05T01:50:51Z"},{"alias_kind":"pith_short_16","alias_value":"KIHZ644YIQ62SHAE","created_at":"2026-07-05T01:50:51Z"},{"alias_kind":"pith_short_8","alias_value":"KIHZ644Y","created_at":"2026-07-05T01:50:51Z"}],"graph_snapshots":[{"event_id":"sha256:69b873a2ebe7edc22545e457cc210688e11794719aec24b9ee5fa65573427045","target":"graph","created_at":"2026-07-05T01:50:51Z","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/2011.05541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing agile behaviors for legged robots remains a challenging problem. While deep reinforcement learning is a promising approach, learning truly agile behaviors typically requires tedious reward shaping and careful curriculum design. We formulate agile locomotion as a multi-stage learning problem in which a mentor guides the agent throughout the training. The mentor is optimized to place a checkpoint to guide the movement of the robot's center of mass while the student (i.e. the robot) learns to reach these checkpoints. Once the student can solve the task, we teach the student to perform ","authors_text":"Alejandro Escontrela, Atil Iscen, Deepali Jain, George Yu, Jie Tan, Ken Caluwaerts","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2020-11-11T04:38:52Z","title":"Learning Agile Locomotion Skills with a Mentor"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05541","kind":"arxiv","version":1},"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":"sha256:429d2ea43bc58758bcb9f97f6f6c68768ce93954a88c7a8686139c5637aa7dc8","target":"record","created_at":"2026-07-05T01:50:51Z","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":"9e6c4f0ac640ddc2c27716651a41bff0e5566f4324670366958fb396a587e59f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2020-11-11T04:38:52Z","title_canon_sha256":"8f1808845881397d9ca10e7184bc37b56eff7c7cd0deb834f6870c56837cc5a9"},"schema_version":"1.0","source":{"id":"2011.05541","kind":"arxiv","version":1}},"canonical_sha256":"520f9f7398443da91c0415c53c8f30dbfaf7873bcaaa3ea8ec6f808f2d80179b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"520f9f7398443da91c0415c53c8f30dbfaf7873bcaaa3ea8ec6f808f2d80179b","first_computed_at":"2026-07-05T01:50:51.065765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:50:51.065765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4tG75rrcblPPMJ36Zg8SyHfxqimiBFLA3rXevtXPLwAXEVvm0sPmbFzlqPGjtMHlFjw9Fm8c5OvHOsxiO852BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:50:51.066287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.05541","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:429d2ea43bc58758bcb9f97f6f6c68768ce93954a88c7a8686139c5637aa7dc8","sha256:69b873a2ebe7edc22545e457cc210688e11794719aec24b9ee5fa65573427045"],"state_sha256":"77cafec1e4131e94d99a465e40078ca88901b0ee7eb0639e66f70bfc2d22deab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k71iLCW0ElnMmU8aycoywoEVm+ADz/O51EOODukL0oXAB1WrEVzOYkzwr1vEBDs5+t8kV0oRvOBVJXtkAN0TDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T17:52:04.309643Z","bundle_sha256":"116dd5484a4b57e19dcb2f3617ed45934dad8333158877ebe2244f764bc92720"}}