{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4E3CJZ7IWOUD6YJXMRLBEYA54Z","short_pith_number":"pith:4E3CJZ7I","schema_version":"1.0","canonical_sha256":"e13624e7e8b3a83f6137645612601de67d433bd11b0e36222fbac9f799d5cad3","source":{"kind":"arxiv","id":"2506.20307","version":1},"attestation_state":"computed","paper":{"title":"Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David M. Bossens, Heyang Zhao, Ivor W. Tsang, Quanquan Gu, Xingrui Yu","submitted_at":"2025-06-25T10:39:32Z","abstract_excerpt":"Imitation learning is a central problem in reinforcement learning where the goal is to learn a policy that mimics the expert's behavior. In practice, it is often challenging to learn the expert policy from a limited number of demonstrations accurately due to the complexity of the state space. Moreover, it is essential to explore the environment and collect data to achieve beyond-expert performance. To overcome these challenges, we propose a novel imitation learning algorithm called Imitation Learning with Double Exploration (ILDE), which implements exploration in two aspects: (1) optimistic po"},"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":"2506.20307","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T10:39:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"24dc8f57dec58bdce3e1aa588006bac9b097916cb1e1757707ac9350a6b75e3e","abstract_canon_sha256":"28e905db61a75de1508e757bab2b8ccc1c2d61853be6640babd1f1815ebd8619"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:03.601214Z","signature_b64":"rbsIpyEYgiUEE1yYhmGG3SZtPV5UKTCEyoGin5EFBKQ5zkNeygORaxZXdDPU0yRndrR+iqVKpeA+ZzoHDod7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e13624e7e8b3a83f6137645612601de67d433bd11b0e36222fbac9f799d5cad3","last_reissued_at":"2026-07-05T11:27:03.600796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:03.600796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David M. Bossens, Heyang Zhao, Ivor W. Tsang, Quanquan Gu, Xingrui Yu","submitted_at":"2025-06-25T10:39:32Z","abstract_excerpt":"Imitation learning is a central problem in reinforcement learning where the goal is to learn a policy that mimics the expert's behavior. In practice, it is often challenging to learn the expert policy from a limited number of demonstrations accurately due to the complexity of the state space. Moreover, it is essential to explore the environment and collect data to achieve beyond-expert performance. To overcome these challenges, we propose a novel imitation learning algorithm called Imitation Learning with Double Exploration (ILDE), which implements exploration in two aspects: (1) optimistic po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20307","kind":"arxiv","version":1},"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/2506.20307/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":"2506.20307","created_at":"2026-07-05T11:27:03.600861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20307v1","created_at":"2026-07-05T11:27:03.600861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20307","created_at":"2026-07-05T11:27:03.600861+00:00"},{"alias_kind":"pith_short_12","alias_value":"4E3CJZ7IWOUD","created_at":"2026-07-05T11:27:03.600861+00:00"},{"alias_kind":"pith_short_16","alias_value":"4E3CJZ7IWOUD6YJX","created_at":"2026-07-05T11:27:03.600861+00:00"},{"alias_kind":"pith_short_8","alias_value":"4E3CJZ7I","created_at":"2026-07-05T11:27:03.600861+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/4E3CJZ7IWOUD6YJXMRLBEYA54Z","json":"https://pith.science/pith/4E3CJZ7IWOUD6YJXMRLBEYA54Z.json","graph_json":"https://pith.science/api/pith-number/4E3CJZ7IWOUD6YJXMRLBEYA54Z/graph.json","events_json":"https://pith.science/api/pith-number/4E3CJZ7IWOUD6YJXMRLBEYA54Z/events.json","paper":"https://pith.science/paper/4E3CJZ7I"},"agent_actions":{"view_html":"https://pith.science/pith/4E3CJZ7IWOUD6YJXMRLBEYA54Z","download_json":"https://pith.science/pith/4E3CJZ7IWOUD6YJXMRLBEYA54Z.json","view_paper":"https://pith.science/paper/4E3CJZ7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20307&json=true","fetch_graph":"https://pith.science/api/pith-number/4E3CJZ7IWOUD6YJXMRLBEYA54Z/graph.json","fetch_events":"https://pith.science/api/pith-number/4E3CJZ7IWOUD6YJXMRLBEYA54Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4E3CJZ7IWOUD6YJXMRLBEYA54Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4E3CJZ7IWOUD6YJXMRLBEYA54Z/action/storage_attestation","attest_author":"https://pith.science/pith/4E3CJZ7IWOUD6YJXMRLBEYA54Z/action/author_attestation","sign_citation":"https://pith.science/pith/4E3CJZ7IWOUD6YJXMRLBEYA54Z/action/citation_signature","submit_replication":"https://pith.science/pith/4E3CJZ7IWOUD6YJXMRLBEYA54Z/action/replication_record"}},"created_at":"2026-07-05T11:27:03.600861+00:00","updated_at":"2026-07-05T11:27:03.600861+00:00"}