{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7GV65UZO62O2PQKRF5HFG5FX34","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":"1ae8e2c5cdac2c8ae9f4db6674412c26ac5f5fd797c48b3ba672f3d7c3039536","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-21T04:15:12Z","title_canon_sha256":"2ddabe00673d940e753795d65800e01e8ab6710aadd7d1e7420e693685cfcc9c"},"schema_version":"1.0","source":{"id":"2206.10101","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.10101","created_at":"2026-07-05T04:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2206.10101v2","created_at":"2026-07-05T04:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10101","created_at":"2026-07-05T04:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"7GV65UZO62O2","created_at":"2026-07-05T04:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"7GV65UZO62O2PQKR","created_at":"2026-07-05T04:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"7GV65UZO","created_at":"2026-07-05T04:53:28Z"}],"graph_snapshots":[{"event_id":"sha256:8a7e55362dc3512af59c523b3dfd35daca31d9904dbaa6354395299fd54dd62b","target":"graph","created_at":"2026-07-05T04:53:28Z","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/2206.10101/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Approaches based on generative adversarial networks for imitation learning are promising because they are sample efficient in terms of expert demonstrations. However, training a generator requires many interactions with the actual environment because model-free reinforcement learning is adopted to update a policy. To improve the sample efficiency using model-based reinforcement learning, we propose model-based Entropy-Regularized Imitation Learning (MB-ERIL) under the entropy-regularized Markov decision process to reduce the number of interactions with the actual environment. MB-ERIL uses two ","authors_text":"Eiji Uchibe","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-21T04:15:12Z","title":"Model-Based Imitation Learning Using Entropy Regularization of Model and Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.10101","kind":"arxiv","version":2},"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":"sha256:569610198ec96c016de7eddfb4b5f733b8ade4d172f20355a39ee9909860de45","target":"record","created_at":"2026-07-05T04:53:28Z","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":"1ae8e2c5cdac2c8ae9f4db6674412c26ac5f5fd797c48b3ba672f3d7c3039536","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-21T04:15:12Z","title_canon_sha256":"2ddabe00673d940e753795d65800e01e8ab6710aadd7d1e7420e693685cfcc9c"},"schema_version":"1.0","source":{"id":"2206.10101","kind":"arxiv","version":2}},"canonical_sha256":"f9abeed32ef69da7c1512f4e5374b7df33b7038c7321746b321da60f9f855c78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9abeed32ef69da7c1512f4e5374b7df33b7038c7321746b321da60f9f855c78","first_computed_at":"2026-07-05T04:53:28.920183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:53:28.920183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"usjOwkRFamaPP2Ywus2csFwj74tf2fuuKnM58S8MRnIZH8g4FlZcpbSzI5O8ymExd7jchnsogf+yDHB5GytjBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:53:28.920522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.10101","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:569610198ec96c016de7eddfb4b5f733b8ade4d172f20355a39ee9909860de45","sha256:8a7e55362dc3512af59c523b3dfd35daca31d9904dbaa6354395299fd54dd62b"],"state_sha256":"dd95a3cc2f632ad11068e764c04b6e7c7ddd8c592cdaa5cafc05ba011240811c"}