{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZG3DI7JVXUCIIRJDUBKE6HQT6K","short_pith_number":"pith:ZG3DI7JV","schema_version":"1.0","canonical_sha256":"c9b6347d35bd04844523a0544f1e13f2a8e698aa9ca63dd535a7c3475debaf11","source":{"kind":"arxiv","id":"1812.01483","version":2},"attestation_state":"computed","paper":{"title":"CompILE: Compositional Imitation Learning and Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alvaro Sanchez-Gonzalez, Edward Grefenstette, Hanjun Dai, Peter Battaglia, Pushmeet Kohli, Thomas Kipf, Vinicius Zambaldi, Yujia Li","submitted_at":"2018-12-04T15:23:50Z","abstract_excerpt":"We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised, fully-differentiable sequence segmentation module to learn latent encodings of sequential data that can be re-composed and executed to perform new tasks. Once trained, our model generalizes to sequences of longer length and from environment instances not seen during training. We evaluate CompILE in a challenging 2D multi-task environment and a continuous control task, "},"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":"1812.01483","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-04T15:23:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"adb20de6ba16df565f3ca5bfb6eee1ed6353cbfb64689f78be51503984cd6462","abstract_canon_sha256":"f913f06cdcab24208d8e1722bfc3e0fb42d1544865777324032abd3e4dd683c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:19.058218Z","signature_b64":"xsBr6vAr/Gb/D+F4eK+bU5m/B0RrmoVoOwSnA0TOZDTbOnGI9bA4mtvSW+D3SWR9V9hl6cXXxSAGi0QDYBsLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9b6347d35bd04844523a0544f1e13f2a8e698aa9ca63dd535a7c3475debaf11","last_reissued_at":"2026-05-17T23:46:19.057486Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:19.057486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CompILE: Compositional Imitation Learning and Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alvaro Sanchez-Gonzalez, Edward Grefenstette, Hanjun Dai, Peter Battaglia, Pushmeet Kohli, Thomas Kipf, Vinicius Zambaldi, Yujia Li","submitted_at":"2018-12-04T15:23:50Z","abstract_excerpt":"We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised, fully-differentiable sequence segmentation module to learn latent encodings of sequential data that can be re-composed and executed to perform new tasks. Once trained, our model generalizes to sequences of longer length and from environment instances not seen during training. We evaluate CompILE in a challenging 2D multi-task environment and a continuous control task, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01483","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1812.01483","created_at":"2026-05-17T23:46:19.057620+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.01483v2","created_at":"2026-05-17T23:46:19.057620+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01483","created_at":"2026-05-17T23:46:19.057620+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZG3DI7JVXUCI","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZG3DI7JVXUCIIRJD","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZG3DI7JV","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.00664","citing_title":"Learning World Graphs to Accelerate Hierarchical Reinforcement Learning","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZG3DI7JVXUCIIRJDUBKE6HQT6K","json":"https://pith.science/pith/ZG3DI7JVXUCIIRJDUBKE6HQT6K.json","graph_json":"https://pith.science/api/pith-number/ZG3DI7JVXUCIIRJDUBKE6HQT6K/graph.json","events_json":"https://pith.science/api/pith-number/ZG3DI7JVXUCIIRJDUBKE6HQT6K/events.json","paper":"https://pith.science/paper/ZG3DI7JV"},"agent_actions":{"view_html":"https://pith.science/pith/ZG3DI7JVXUCIIRJDUBKE6HQT6K","download_json":"https://pith.science/pith/ZG3DI7JVXUCIIRJDUBKE6HQT6K.json","view_paper":"https://pith.science/paper/ZG3DI7JV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.01483&json=true","fetch_graph":"https://pith.science/api/pith-number/ZG3DI7JVXUCIIRJDUBKE6HQT6K/graph.json","fetch_events":"https://pith.science/api/pith-number/ZG3DI7JVXUCIIRJDUBKE6HQT6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZG3DI7JVXUCIIRJDUBKE6HQT6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZG3DI7JVXUCIIRJDUBKE6HQT6K/action/storage_attestation","attest_author":"https://pith.science/pith/ZG3DI7JVXUCIIRJDUBKE6HQT6K/action/author_attestation","sign_citation":"https://pith.science/pith/ZG3DI7JVXUCIIRJDUBKE6HQT6K/action/citation_signature","submit_replication":"https://pith.science/pith/ZG3DI7JVXUCIIRJDUBKE6HQT6K/action/replication_record"}},"created_at":"2026-05-17T23:46:19.057620+00:00","updated_at":"2026-05-17T23:46:19.057620+00:00"}