{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H5DW7VFOBR5K7NUXDBTLRMGRRN","short_pith_number":"pith:H5DW7VFO","schema_version":"1.0","canonical_sha256":"3f476fd4ae0c7aafb6971866b8b0d18b6da42aec43c0957876b8165d82b2dc1d","source":{"kind":"arxiv","id":"2401.09728","version":1},"attestation_state":"computed","paper":{"title":"Offline Imitation Learning by Controlling the Effective Planning Horizon","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Byung-Jun Lee, Hee-Jun Ahn, Seong-Woong Shim","submitted_at":"2024-01-18T05:17:30Z","abstract_excerpt":"In offline imitation learning (IL), we generally assume only a handful of expert trajectories and a supplementary offline dataset from suboptimal behaviors to learn the expert policy. While it is now common to minimize the divergence between state-action visitation distributions so that the agent also considers the future consequences of an action, a sampling error in an offline dataset may lead to erroneous estimates of state-action visitations in the offline case. In this paper, we investigate the effect of controlling the effective planning horizon (i.e., reducing the discount factor) as op"},"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":"2401.09728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T05:17:30Z","cross_cats_sorted":[],"title_canon_sha256":"e8178321879824a5f1b4f407f4b753480907b12dbe8c7d93b57dcde7297d7d42","abstract_canon_sha256":"c4dec64715e3da9e7eff690eb58b39b83953be478fc1a12d46e4faaa69628820"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:01.339152Z","signature_b64":"coyNycI54YTDxuwy1lAdtlbAiOZqjZt8oWGiNoCiD9wlsR0Js7shQR+SdNfx5vfzJymlAIdiA9zbW/uF7a7tCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f476fd4ae0c7aafb6971866b8b0d18b6da42aec43c0957876b8165d82b2dc1d","last_reissued_at":"2026-07-05T07:35:01.338649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:01.338649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Imitation Learning by Controlling the Effective Planning Horizon","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Byung-Jun Lee, Hee-Jun Ahn, Seong-Woong Shim","submitted_at":"2024-01-18T05:17:30Z","abstract_excerpt":"In offline imitation learning (IL), we generally assume only a handful of expert trajectories and a supplementary offline dataset from suboptimal behaviors to learn the expert policy. While it is now common to minimize the divergence between state-action visitation distributions so that the agent also considers the future consequences of an action, a sampling error in an offline dataset may lead to erroneous estimates of state-action visitations in the offline case. In this paper, we investigate the effect of controlling the effective planning horizon (i.e., reducing the discount factor) as op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09728","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/2401.09728/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":"2401.09728","created_at":"2026-07-05T07:35:01.338719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.09728v1","created_at":"2026-07-05T07:35:01.338719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09728","created_at":"2026-07-05T07:35:01.338719+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5DW7VFOBR5K","created_at":"2026-07-05T07:35:01.338719+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5DW7VFOBR5K7NUX","created_at":"2026-07-05T07:35:01.338719+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5DW7VFO","created_at":"2026-07-05T07:35:01.338719+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/H5DW7VFOBR5K7NUXDBTLRMGRRN","json":"https://pith.science/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN.json","graph_json":"https://pith.science/api/pith-number/H5DW7VFOBR5K7NUXDBTLRMGRRN/graph.json","events_json":"https://pith.science/api/pith-number/H5DW7VFOBR5K7NUXDBTLRMGRRN/events.json","paper":"https://pith.science/paper/H5DW7VFO"},"agent_actions":{"view_html":"https://pith.science/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN","download_json":"https://pith.science/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN.json","view_paper":"https://pith.science/paper/H5DW7VFO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.09728&json=true","fetch_graph":"https://pith.science/api/pith-number/H5DW7VFOBR5K7NUXDBTLRMGRRN/graph.json","fetch_events":"https://pith.science/api/pith-number/H5DW7VFOBR5K7NUXDBTLRMGRRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN/action/storage_attestation","attest_author":"https://pith.science/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN/action/author_attestation","sign_citation":"https://pith.science/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN/action/citation_signature","submit_replication":"https://pith.science/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN/action/replication_record"}},"created_at":"2026-07-05T07:35:01.338719+00:00","updated_at":"2026-07-05T07:35:01.338719+00:00"}