{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YF5CD36C6VX362OAUUXSQCBHHR","short_pith_number":"pith:YF5CD36C","schema_version":"1.0","canonical_sha256":"c17a21efc2f56fbf69c0a52f2808273c69c776f40110beaeaeca2ce025cacb8f","source":{"kind":"arxiv","id":"2206.11693","version":3},"attestation_state":"computed","paper":{"title":"Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chenhao Li, Felix Grimminger, Georg Martius, Jonas Frey, Marin Vlastelica, Sebastian Blaes","submitted_at":"2022-06-23T13:34:11Z","abstract_excerpt":"Learning agile skills is one of the main challenges in robotics. To this end, reinforcement learning approaches have achieved impressive results. These methods require explicit task information in terms of a reward function or an expert that can be queried in simulation to provide a target control output, which limits their applicability. In this work, we propose a generative adversarial method for inferring reward functions from partial and potentially physically incompatible demonstrations for successful skill acquirement where reference or expert demonstrations are not easily accessible. Mo"},"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":"2206.11693","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-06-23T13:34:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0602d6fe60c87453dbed9e9e46856926563db5e9dea30c5ca7576c01dcd8c8d0","abstract_canon_sha256":"51103b848bcbcd535c9f6c8ea8dca4d904ece88f2e22a2b6f6b19d9024eb808f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:46.686394Z","signature_b64":"S0RM7wNlIaa1zQw8ASfDBjG/AQU2EiYDlUxAjmEDPLAew7ivxHhRszk8bnuZP2oqyU163nl0F+oKDtywMyjbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c17a21efc2f56fbf69c0a52f2808273c69c776f40110beaeaeca2ce025cacb8f","last_reissued_at":"2026-07-05T05:17:46.685932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:46.685932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chenhao Li, Felix Grimminger, Georg Martius, Jonas Frey, Marin Vlastelica, Sebastian Blaes","submitted_at":"2022-06-23T13:34:11Z","abstract_excerpt":"Learning agile skills is one of the main challenges in robotics. To this end, reinforcement learning approaches have achieved impressive results. These methods require explicit task information in terms of a reward function or an expert that can be queried in simulation to provide a target control output, which limits their applicability. In this work, we propose a generative adversarial method for inferring reward functions from partial and potentially physically incompatible demonstrations for successful skill acquirement where reference or expert demonstrations are not easily accessible. Mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.11693","kind":"arxiv","version":3},"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/2206.11693/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":"2206.11693","created_at":"2026-07-05T05:17:46.685988+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.11693v3","created_at":"2026-07-05T05:17:46.685988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.11693","created_at":"2026-07-05T05:17:46.685988+00:00"},{"alias_kind":"pith_short_12","alias_value":"YF5CD36C6VX3","created_at":"2026-07-05T05:17:46.685988+00:00"},{"alias_kind":"pith_short_16","alias_value":"YF5CD36C6VX362OA","created_at":"2026-07-05T05:17:46.685988+00:00"},{"alias_kind":"pith_short_8","alias_value":"YF5CD36C","created_at":"2026-07-05T05:17:46.685988+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26392","citing_title":"MPC-Injection: Biasing Off-Policy Locomotion RL Toward Controller-Induced Behavior Basins","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YF5CD36C6VX362OAUUXSQCBHHR","json":"https://pith.science/pith/YF5CD36C6VX362OAUUXSQCBHHR.json","graph_json":"https://pith.science/api/pith-number/YF5CD36C6VX362OAUUXSQCBHHR/graph.json","events_json":"https://pith.science/api/pith-number/YF5CD36C6VX362OAUUXSQCBHHR/events.json","paper":"https://pith.science/paper/YF5CD36C"},"agent_actions":{"view_html":"https://pith.science/pith/YF5CD36C6VX362OAUUXSQCBHHR","download_json":"https://pith.science/pith/YF5CD36C6VX362OAUUXSQCBHHR.json","view_paper":"https://pith.science/paper/YF5CD36C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.11693&json=true","fetch_graph":"https://pith.science/api/pith-number/YF5CD36C6VX362OAUUXSQCBHHR/graph.json","fetch_events":"https://pith.science/api/pith-number/YF5CD36C6VX362OAUUXSQCBHHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YF5CD36C6VX362OAUUXSQCBHHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YF5CD36C6VX362OAUUXSQCBHHR/action/storage_attestation","attest_author":"https://pith.science/pith/YF5CD36C6VX362OAUUXSQCBHHR/action/author_attestation","sign_citation":"https://pith.science/pith/YF5CD36C6VX362OAUUXSQCBHHR/action/citation_signature","submit_replication":"https://pith.science/pith/YF5CD36C6VX362OAUUXSQCBHHR/action/replication_record"}},"created_at":"2026-07-05T05:17:46.685988+00:00","updated_at":"2026-07-05T05:17:46.685988+00:00"}