{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MGJUI7G4ZYG3YEMYKOY4ZRPSNT","short_pith_number":"pith:MGJUI7G4","schema_version":"1.0","canonical_sha256":"6193447cdcce0dbc119853b1ccc5f26ce48234c6dcba2adf5a048600e2d55508","source":{"kind":"arxiv","id":"2112.08932","version":3},"attestation_state":"computed","paper":{"title":"Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bryan Chan, Jonathan Kelly, Trevor Ablett","submitted_at":"2021-12-16T14:58:08Z","abstract_excerpt":"Effective exploration continues to be a significant challenge that prevents the deployment of reinforcement learning for many physical systems. This is particularly true for systems with continuous and high-dimensional state and action spaces, such as robotic manipulators. The challenge is accentuated in the sparse rewards setting, where the low-level state information required for the design of dense rewards is unavailable. Adversarial imitation learning (AIL) can partially overcome this barrier by leveraging expert-generated demonstrations of optimal behaviour and providing, essentially, a r"},"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":"2112.08932","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-16T14:58:08Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"e9ceaef7a37da6dc582214329c07d4c9e5f3cc51244b9d5224d94ce11eedec25","abstract_canon_sha256":"8bae068c034f0230ec278b833b1683ea380ebb20a4e22fafdc33f23e9d377023"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:53.130079Z","signature_b64":"EKm1Jf0dRgj1QT7EoTEIJuhLQjmtrjoNOsEb7T+bN+Gr9J4GQHrLgWIbBUX5FHRtsnyr60J5qP5IjwvtcKMSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6193447cdcce0dbc119853b1ccc5f26ce48234c6dcba2adf5a048600e2d55508","last_reissued_at":"2026-07-05T04:41:53.129660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:53.129660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bryan Chan, Jonathan Kelly, Trevor Ablett","submitted_at":"2021-12-16T14:58:08Z","abstract_excerpt":"Effective exploration continues to be a significant challenge that prevents the deployment of reinforcement learning for many physical systems. This is particularly true for systems with continuous and high-dimensional state and action spaces, such as robotic manipulators. The challenge is accentuated in the sparse rewards setting, where the low-level state information required for the design of dense rewards is unavailable. Adversarial imitation learning (AIL) can partially overcome this barrier by leveraging expert-generated demonstrations of optimal behaviour and providing, essentially, a r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08932","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/2112.08932/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":"2112.08932","created_at":"2026-07-05T04:41:53.129707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08932v3","created_at":"2026-07-05T04:41:53.129707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08932","created_at":"2026-07-05T04:41:53.129707+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGJUI7G4ZYG3","created_at":"2026-07-05T04:41:53.129707+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGJUI7G4ZYG3YEMY","created_at":"2026-07-05T04:41:53.129707+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGJUI7G4","created_at":"2026-07-05T04:41:53.129707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MGJUI7G4ZYG3YEMYKOY4ZRPSNT","json":"https://pith.science/pith/MGJUI7G4ZYG3YEMYKOY4ZRPSNT.json","graph_json":"https://pith.science/api/pith-number/MGJUI7G4ZYG3YEMYKOY4ZRPSNT/graph.json","events_json":"https://pith.science/api/pith-number/MGJUI7G4ZYG3YEMYKOY4ZRPSNT/events.json","paper":"https://pith.science/paper/MGJUI7G4"},"agent_actions":{"view_html":"https://pith.science/pith/MGJUI7G4ZYG3YEMYKOY4ZRPSNT","download_json":"https://pith.science/pith/MGJUI7G4ZYG3YEMYKOY4ZRPSNT.json","view_paper":"https://pith.science/paper/MGJUI7G4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08932&json=true","fetch_graph":"https://pith.science/api/pith-number/MGJUI7G4ZYG3YEMYKOY4ZRPSNT/graph.json","fetch_events":"https://pith.science/api/pith-number/MGJUI7G4ZYG3YEMYKOY4ZRPSNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGJUI7G4ZYG3YEMYKOY4ZRPSNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGJUI7G4ZYG3YEMYKOY4ZRPSNT/action/storage_attestation","attest_author":"https://pith.science/pith/MGJUI7G4ZYG3YEMYKOY4ZRPSNT/action/author_attestation","sign_citation":"https://pith.science/pith/MGJUI7G4ZYG3YEMYKOY4ZRPSNT/action/citation_signature","submit_replication":"https://pith.science/pith/MGJUI7G4ZYG3YEMYKOY4ZRPSNT/action/replication_record"}},"created_at":"2026-07-05T04:41:53.129707+00:00","updated_at":"2026-07-05T04:41:53.129707+00:00"}