{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KK4EDEUZ2DXBOPMBP7JZKOPBN5","short_pith_number":"pith:KK4EDEUZ","schema_version":"1.0","canonical_sha256":"52b8419299d0ee173d817fd39539e16f4ca5b2f84335ec49d94ca7d1440d9f03","source":{"kind":"arxiv","id":"1805.08336","version":2},"attestation_state":"computed","paper":{"title":"Maximum Causal Tsallis Entropy Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kyungjae Lee, Songhwai Oh, Sungjoon Choi","submitted_at":"2018-05-22T00:49:47Z","abstract_excerpt":"In this paper, we propose a novel maximum causal Tsallis entropy (MCTE) framework for imitation learning which can efficiently learn a sparse multi-modal policy distribution from demonstrations. We provide the full mathematical analysis of the proposed framework. First, the optimal solution of an MCTE problem is shown to be a sparsemax distribution, whose supporting set can be adjusted. The proposed method has advantages over a softmax distribution in that it can exclude unnecessary actions by assigning zero probability. Second, we prove that an MCTE problem is equivalent to robust Bayes estim"},"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":"1805.08336","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-22T00:49:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a4414ad7b08122bc4af31b6eb0ddcac4dcbc5bfaf2e5563210c564898279e039","abstract_canon_sha256":"a51f4d482ce53eb6a4d3807e466d7f18907ecfb458a72ffe4b5e6d290eca6268"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:53.160115Z","signature_b64":"DIqMQCu8I/zSn97Mc+R4VCMp4ncESeEQSKcCiO99hDrrvsnmLioT2BNrEoR2LFUdOWEYXiVv/keThZFlw7VMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52b8419299d0ee173d817fd39539e16f4ca5b2f84335ec49d94ca7d1440d9f03","last_reissued_at":"2026-05-18T00:14:53.159377Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:53.159377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximum Causal Tsallis Entropy Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kyungjae Lee, Songhwai Oh, Sungjoon Choi","submitted_at":"2018-05-22T00:49:47Z","abstract_excerpt":"In this paper, we propose a novel maximum causal Tsallis entropy (MCTE) framework for imitation learning which can efficiently learn a sparse multi-modal policy distribution from demonstrations. We provide the full mathematical analysis of the proposed framework. First, the optimal solution of an MCTE problem is shown to be a sparsemax distribution, whose supporting set can be adjusted. The proposed method has advantages over a softmax distribution in that it can exclude unnecessary actions by assigning zero probability. Second, we prove that an MCTE problem is equivalent to robust Bayes estim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08336","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":"1805.08336","created_at":"2026-05-18T00:14:53.159494+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08336v2","created_at":"2026-05-18T00:14:53.159494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08336","created_at":"2026-05-18T00:14:53.159494+00:00"},{"alias_kind":"pith_short_12","alias_value":"KK4EDEUZ2DXB","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KK4EDEUZ2DXBOPMB","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KK4EDEUZ","created_at":"2026-05-18T12:32:33.847187+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/KK4EDEUZ2DXBOPMBP7JZKOPBN5","json":"https://pith.science/pith/KK4EDEUZ2DXBOPMBP7JZKOPBN5.json","graph_json":"https://pith.science/api/pith-number/KK4EDEUZ2DXBOPMBP7JZKOPBN5/graph.json","events_json":"https://pith.science/api/pith-number/KK4EDEUZ2DXBOPMBP7JZKOPBN5/events.json","paper":"https://pith.science/paper/KK4EDEUZ"},"agent_actions":{"view_html":"https://pith.science/pith/KK4EDEUZ2DXBOPMBP7JZKOPBN5","download_json":"https://pith.science/pith/KK4EDEUZ2DXBOPMBP7JZKOPBN5.json","view_paper":"https://pith.science/paper/KK4EDEUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08336&json=true","fetch_graph":"https://pith.science/api/pith-number/KK4EDEUZ2DXBOPMBP7JZKOPBN5/graph.json","fetch_events":"https://pith.science/api/pith-number/KK4EDEUZ2DXBOPMBP7JZKOPBN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KK4EDEUZ2DXBOPMBP7JZKOPBN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KK4EDEUZ2DXBOPMBP7JZKOPBN5/action/storage_attestation","attest_author":"https://pith.science/pith/KK4EDEUZ2DXBOPMBP7JZKOPBN5/action/author_attestation","sign_citation":"https://pith.science/pith/KK4EDEUZ2DXBOPMBP7JZKOPBN5/action/citation_signature","submit_replication":"https://pith.science/pith/KK4EDEUZ2DXBOPMBP7JZKOPBN5/action/replication_record"}},"created_at":"2026-05-18T00:14:53.159494+00:00","updated_at":"2026-05-18T00:14:53.159494+00:00"}