{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MGJUI7G4ZYG3YEMYKOY4ZRPSNT","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":"8bae068c034f0230ec278b833b1683ea380ebb20a4e22fafdc33f23e9d377023","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-16T14:58:08Z","title_canon_sha256":"e9ceaef7a37da6dc582214329c07d4c9e5f3cc51244b9d5224d94ce11eedec25"},"schema_version":"1.0","source":{"id":"2112.08932","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08932","created_at":"2026-07-05T04:41:53Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08932v3","created_at":"2026-07-05T04:41:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08932","created_at":"2026-07-05T04:41:53Z"},{"alias_kind":"pith_short_12","alias_value":"MGJUI7G4ZYG3","created_at":"2026-07-05T04:41:53Z"},{"alias_kind":"pith_short_16","alias_value":"MGJUI7G4ZYG3YEMY","created_at":"2026-07-05T04:41:53Z"},{"alias_kind":"pith_short_8","alias_value":"MGJUI7G4","created_at":"2026-07-05T04:41:53Z"}],"graph_snapshots":[{"event_id":"sha256:fc1fabee67605953270a464ea988c540ab73148bb82f700d5686ab4d583b1930","target":"graph","created_at":"2026-07-05T04:41:53Z","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/2112.08932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bryan Chan, Jonathan Kelly, Trevor Ablett","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-16T14:58:08Z","title":"Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08932","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":"sha256:7a66f35116b80895a0a98962df308e43daaee3e4a2dacf0f104e828cff75e690","target":"record","created_at":"2026-07-05T04:41:53Z","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":"8bae068c034f0230ec278b833b1683ea380ebb20a4e22fafdc33f23e9d377023","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-16T14:58:08Z","title_canon_sha256":"e9ceaef7a37da6dc582214329c07d4c9e5f3cc51244b9d5224d94ce11eedec25"},"schema_version":"1.0","source":{"id":"2112.08932","kind":"arxiv","version":3}},"canonical_sha256":"6193447cdcce0dbc119853b1ccc5f26ce48234c6dcba2adf5a048600e2d55508","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6193447cdcce0dbc119853b1ccc5f26ce48234c6dcba2adf5a048600e2d55508","first_computed_at":"2026-07-05T04:41:53.129660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:41:53.129660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EKm1Jf0dRgj1QT7EoTEIJuhLQjmtrjoNOsEb7T+bN+Gr9J4GQHrLgWIbBUX5FHRtsnyr60J5qP5IjwvtcKMSBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:41:53.130079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08932","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a66f35116b80895a0a98962df308e43daaee3e4a2dacf0f104e828cff75e690","sha256:fc1fabee67605953270a464ea988c540ab73148bb82f700d5686ab4d583b1930"],"state_sha256":"0d61f3671c3c1d19aec731c98aae859b3a9aaec9dcb9b116d2cca09bdedeaddb"}