{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BFM3LT556XK4OAIEOYFYTJ4232","short_pith_number":"pith:BFM3LT55","schema_version":"1.0","canonical_sha256":"0959b5cfbdf5d5c70104760b89a79ade9a91e126ca41b7ccb81d3fee8c1db4bf","source":{"kind":"arxiv","id":"1805.11240","version":1},"attestation_state":"computed","paper":{"title":"Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Byron Boots, J. Andrew Bagnell, Wen Sun","submitted_at":"2018-05-29T04:24:17Z","abstract_excerpt":"In this paper, we propose to combine imitation and reinforcement learning via the idea of reward shaping using an oracle. We study the effectiveness of the near-optimal cost-to-go oracle on the planning horizon and demonstrate that the cost-to-go oracle shortens the learner's planning horizon as function of its accuracy: a globally optimal oracle can shorten the planning horizon to one, leading to a one-step greedy Markov Decision Process which is much easier to optimize, while an oracle that is far away from the optimality requires planning over a longer horizon to achieve near-optimal perfor"},"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":"1805.11240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T04:24:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7d41c03c29e2cefa7238144e645f5231c77f9415331e3c5da7701ba5a7cf10d3","abstract_canon_sha256":"81ed4da67a4e22409ed313913c1321fb6422d07afcfff4f741cd7b586c01dba4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:43.316168Z","signature_b64":"eJEIe9DquTTpg19fEa1xnRP5VKrNMrqo+W/7YOjmG1lxwNNHp6dO33bpG6Lhqu4Ixv0c+KwNtia41zsAulAVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0959b5cfbdf5d5c70104760b89a79ade9a91e126ca41b7ccb81d3fee8c1db4bf","last_reissued_at":"2026-05-18T00:14:43.315545Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:43.315545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Byron Boots, J. Andrew Bagnell, Wen Sun","submitted_at":"2018-05-29T04:24:17Z","abstract_excerpt":"In this paper, we propose to combine imitation and reinforcement learning via the idea of reward shaping using an oracle. We study the effectiveness of the near-optimal cost-to-go oracle on the planning horizon and demonstrate that the cost-to-go oracle shortens the learner's planning horizon as function of its accuracy: a globally optimal oracle can shorten the planning horizon to one, leading to a one-step greedy Markov Decision Process which is much easier to optimize, while an oracle that is far away from the optimality requires planning over a longer horizon to achieve near-optimal perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11240","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":""},"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":"1805.11240","created_at":"2026-05-18T00:14:43.315632+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.11240v1","created_at":"2026-05-18T00:14:43.315632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11240","created_at":"2026-05-18T00:14:43.315632+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFM3LT556XK4","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFM3LT556XK4OAIE","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFM3LT55","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.07238","citing_title":"Leveraging Experience in Lazy Search","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BFM3LT556XK4OAIEOYFYTJ4232","json":"https://pith.science/pith/BFM3LT556XK4OAIEOYFYTJ4232.json","graph_json":"https://pith.science/api/pith-number/BFM3LT556XK4OAIEOYFYTJ4232/graph.json","events_json":"https://pith.science/api/pith-number/BFM3LT556XK4OAIEOYFYTJ4232/events.json","paper":"https://pith.science/paper/BFM3LT55"},"agent_actions":{"view_html":"https://pith.science/pith/BFM3LT556XK4OAIEOYFYTJ4232","download_json":"https://pith.science/pith/BFM3LT556XK4OAIEOYFYTJ4232.json","view_paper":"https://pith.science/paper/BFM3LT55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.11240&json=true","fetch_graph":"https://pith.science/api/pith-number/BFM3LT556XK4OAIEOYFYTJ4232/graph.json","fetch_events":"https://pith.science/api/pith-number/BFM3LT556XK4OAIEOYFYTJ4232/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFM3LT556XK4OAIEOYFYTJ4232/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFM3LT556XK4OAIEOYFYTJ4232/action/storage_attestation","attest_author":"https://pith.science/pith/BFM3LT556XK4OAIEOYFYTJ4232/action/author_attestation","sign_citation":"https://pith.science/pith/BFM3LT556XK4OAIEOYFYTJ4232/action/citation_signature","submit_replication":"https://pith.science/pith/BFM3LT556XK4OAIEOYFYTJ4232/action/replication_record"}},"created_at":"2026-05-18T00:14:43.315632+00:00","updated_at":"2026-05-18T00:14:43.315632+00:00"}