{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:BFM3LT556XK4OAIEOYFYTJ4232","short_pith_number":"pith:BFM3LT55","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"},"canonical_sha256":"0959b5cfbdf5d5c70104760b89a79ade9a91e126ca41b7ccb81d3fee8c1db4bf","source":{"kind":"arxiv","id":"1805.11240","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11240","created_at":"2026-05-18T00:14:43Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11240v1","created_at":"2026-05-18T00:14:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11240","created_at":"2026-05-18T00:14:43Z"},{"alias_kind":"pith_short_12","alias_value":"BFM3LT556XK4","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BFM3LT556XK4OAIE","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BFM3LT55","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:BFM3LT556XK4OAIEOYFYTJ4232","target":"record","payload":{"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"},"canonical_sha256":"0959b5cfbdf5d5c70104760b89a79ade9a91e126ca41b7ccb81d3fee8c1db4bf","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"},"source_kind":"arxiv","source_id":"1805.11240","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nZono6tg5Eda+3Hd5HdFWoh0es2uETFLx5KSxco+RTe/UWiswfpVp80xTjEUPS4jwKhYVp3TDlX3kpyGcsG8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T00:16:40.882937Z"},"content_sha256":"96de5d98489e33c5a670cc98b668a6e6e0c6a88bb6ffeae13e0518112f937351","schema_version":"1.0","event_id":"sha256:96de5d98489e33c5a670cc98b668a6e6e0c6a88bb6ffeae13e0518112f937351"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:BFM3LT556XK4OAIEOYFYTJ4232","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YKIhQ+JtSm7E8ucffV/IHgPTEZKEoL5qYqoWLEDlSrdJdV0LmC8Gx8u08s8XJc2K1LWGe80A+vENrn7uIAt5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T00:16:40.883333Z"},"content_sha256":"eee9077868c035d741ff7e4d6c8194e8432619b4572f28058f7beace40586ec4","schema_version":"1.0","event_id":"sha256:eee9077868c035d741ff7e4d6c8194e8432619b4572f28058f7beace40586ec4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BFM3LT556XK4OAIEOYFYTJ4232/bundle.json","state_url":"https://pith.science/pith/BFM3LT556XK4OAIEOYFYTJ4232/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BFM3LT556XK4OAIEOYFYTJ4232/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T00:16:40Z","links":{"resolver":"https://pith.science/pith/BFM3LT556XK4OAIEOYFYTJ4232","bundle":"https://pith.science/pith/BFM3LT556XK4OAIEOYFYTJ4232/bundle.json","state":"https://pith.science/pith/BFM3LT556XK4OAIEOYFYTJ4232/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BFM3LT556XK4OAIEOYFYTJ4232/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:BFM3LT556XK4OAIEOYFYTJ4232","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"81ed4da67a4e22409ed313913c1321fb6422d07afcfff4f741cd7b586c01dba4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T04:24:17Z","title_canon_sha256":"7d41c03c29e2cefa7238144e645f5231c77f9415331e3c5da7701ba5a7cf10d3"},"schema_version":"1.0","source":{"id":"1805.11240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11240","created_at":"2026-05-18T00:14:43Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11240v1","created_at":"2026-05-18T00:14:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11240","created_at":"2026-05-18T00:14:43Z"},{"alias_kind":"pith_short_12","alias_value":"BFM3LT556XK4","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BFM3LT556XK4OAIE","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BFM3LT55","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:eee9077868c035d741ff7e4d6c8194e8432619b4572f28058f7beace40586ec4","target":"graph","created_at":"2026-05-18T00:14:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Byron Boots, J. Andrew Bagnell, Wen Sun","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T04:24:17Z","title":"Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11240","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:96de5d98489e33c5a670cc98b668a6e6e0c6a88bb6ffeae13e0518112f937351","target":"record","created_at":"2026-05-18T00:14:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"81ed4da67a4e22409ed313913c1321fb6422d07afcfff4f741cd7b586c01dba4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T04:24:17Z","title_canon_sha256":"7d41c03c29e2cefa7238144e645f5231c77f9415331e3c5da7701ba5a7cf10d3"},"schema_version":"1.0","source":{"id":"1805.11240","kind":"arxiv","version":1}},"canonical_sha256":"0959b5cfbdf5d5c70104760b89a79ade9a91e126ca41b7ccb81d3fee8c1db4bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0959b5cfbdf5d5c70104760b89a79ade9a91e126ca41b7ccb81d3fee8c1db4bf","first_computed_at":"2026-05-18T00:14:43.315545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:43.315545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eJEIe9DquTTpg19fEa1xnRP5VKrNMrqo+W/7YOjmG1lxwNNHp6dO33bpG6Lhqu4Ixv0c+KwNtia41zsAulAVAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:43.316168Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.11240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96de5d98489e33c5a670cc98b668a6e6e0c6a88bb6ffeae13e0518112f937351","sha256:eee9077868c035d741ff7e4d6c8194e8432619b4572f28058f7beace40586ec4"],"state_sha256":"93b414f9920af363d072ad453a793a8028d36fd26bce86b6414f9caaea319382"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RzeTojuIp9Jb36MKYyAVyuD8/prtiEuTSaJoPr2pTH+sLh9Qgi4DFDlkX5eqsQv19l9aevUjwldhs4fSTFGNDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T00:16:40.886342Z","bundle_sha256":"990c42e18c43a00608510a662b81976b686ce5a03ccdace12ca75590d9f0efa2"}}