{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QCLDBS4DUFEIEWH75XKOQR3KUG","short_pith_number":"pith:QCLDBS4D","schema_version":"1.0","canonical_sha256":"809630cb83a1488258ffedd4e8476aa197bd77baf3c62a630c62920135e39fac","source":{"kind":"arxiv","id":"2008.00603","version":1},"attestation_state":"computed","paper":{"title":"Learning Agile Locomotion via Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jie Tan, Tatsuya Harada, Yujin Tang","submitted_at":"2020-08-03T01:20:37Z","abstract_excerpt":"Developing controllers for agile locomotion is a long-standing challenge for legged robots. Reinforcement learning (RL) and Evolution Strategy (ES) hold the promise of automating the design process of such controllers. However, dedicated and careful human effort is required to design training environments to promote agility. In this paper, we present a multi-agent learning system, in which a quadruped robot (protagonist) learns to chase another robot (adversary) while the latter learns to escape. We find that this adversarial training process not only encourages agile behaviors but also effect"},"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":"2008.00603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-08-03T01:20:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4138b3985aedaaa10c3a21c1faff119aad5d6038490b29eecb35926edde4093","abstract_canon_sha256":"99ca46efa72312a30650b221c2c5ef52029c52c06e015cc1569b0f118f76d006"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:24:09.177855Z","signature_b64":"cTzRRdP+WcNMB41t4h/V+8kK3FRkStZK+no0xDj4vVEN/SzVtPg5kq8vLwslqJmcsplriQJZLlZ9h3+v8Ry2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"809630cb83a1488258ffedd4e8476aa197bd77baf3c62a630c62920135e39fac","last_reissued_at":"2026-07-05T01:24:09.177471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:24:09.177471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Agile Locomotion via Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jie Tan, Tatsuya Harada, Yujin Tang","submitted_at":"2020-08-03T01:20:37Z","abstract_excerpt":"Developing controllers for agile locomotion is a long-standing challenge for legged robots. Reinforcement learning (RL) and Evolution Strategy (ES) hold the promise of automating the design process of such controllers. However, dedicated and careful human effort is required to design training environments to promote agility. In this paper, we present a multi-agent learning system, in which a quadruped robot (protagonist) learns to chase another robot (adversary) while the latter learns to escape. We find that this adversarial training process not only encourages agile behaviors but also effect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.00603","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/2008.00603/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":"2008.00603","created_at":"2026-07-05T01:24:09.177542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.00603v1","created_at":"2026-07-05T01:24:09.177542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.00603","created_at":"2026-07-05T01:24:09.177542+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCLDBS4DUFEI","created_at":"2026-07-05T01:24:09.177542+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCLDBS4DUFEIEWH7","created_at":"2026-07-05T01:24:09.177542+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCLDBS4D","created_at":"2026-07-05T01:24:09.177542+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03035","citing_title":"UMC: Unified Resilient Controller for Legged Robots with Joint Malfunctions","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QCLDBS4DUFEIEWH75XKOQR3KUG","json":"https://pith.science/pith/QCLDBS4DUFEIEWH75XKOQR3KUG.json","graph_json":"https://pith.science/api/pith-number/QCLDBS4DUFEIEWH75XKOQR3KUG/graph.json","events_json":"https://pith.science/api/pith-number/QCLDBS4DUFEIEWH75XKOQR3KUG/events.json","paper":"https://pith.science/paper/QCLDBS4D"},"agent_actions":{"view_html":"https://pith.science/pith/QCLDBS4DUFEIEWH75XKOQR3KUG","download_json":"https://pith.science/pith/QCLDBS4DUFEIEWH75XKOQR3KUG.json","view_paper":"https://pith.science/paper/QCLDBS4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.00603&json=true","fetch_graph":"https://pith.science/api/pith-number/QCLDBS4DUFEIEWH75XKOQR3KUG/graph.json","fetch_events":"https://pith.science/api/pith-number/QCLDBS4DUFEIEWH75XKOQR3KUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCLDBS4DUFEIEWH75XKOQR3KUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCLDBS4DUFEIEWH75XKOQR3KUG/action/storage_attestation","attest_author":"https://pith.science/pith/QCLDBS4DUFEIEWH75XKOQR3KUG/action/author_attestation","sign_citation":"https://pith.science/pith/QCLDBS4DUFEIEWH75XKOQR3KUG/action/citation_signature","submit_replication":"https://pith.science/pith/QCLDBS4DUFEIEWH75XKOQR3KUG/action/replication_record"}},"created_at":"2026-07-05T01:24:09.177542+00:00","updated_at":"2026-07-05T01:24:09.177542+00:00"}