{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6PCJ27WYGXA45HEQ7EOLGYLFR3","short_pith_number":"pith:6PCJ27WY","canonical_record":{"source":{"id":"1806.04642","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-12T16:55:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9d777e759b4ef471487250305975f28f375d808bc95a1a81f1ddf8be3c7599ec","abstract_canon_sha256":"4ea1353d92a52b81c3eabe1534744857ab97f18409f249c9daaa2f518564a814"},"schema_version":"1.0"},"canonical_sha256":"f3c49d7ed835c1ce9c90f91cb361658ee064e6ad535ab34c5d52b2f3c33b7d3c","source":{"kind":"arxiv","id":"1806.04642","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04642","created_at":"2026-05-18T00:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04642v4","created_at":"2026-05-18T00:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04642","created_at":"2026-05-18T00:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"6PCJ27WYGXA4","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"6PCJ27WYGXA45HEQ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"6PCJ27WY","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6PCJ27WYGXA45HEQ7EOLGYLFR3","target":"record","payload":{"canonical_record":{"source":{"id":"1806.04642","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-12T16:55:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9d777e759b4ef471487250305975f28f375d808bc95a1a81f1ddf8be3c7599ec","abstract_canon_sha256":"4ea1353d92a52b81c3eabe1534744857ab97f18409f249c9daaa2f518564a814"},"schema_version":"1.0"},"canonical_sha256":"f3c49d7ed835c1ce9c90f91cb361658ee064e6ad535ab34c5d52b2f3c33b7d3c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:27.459213Z","signature_b64":"qtbkZouuy9LisoVtbu2IqWSgu9Vka3M62kBKAZCAjTgPP0WzW+XbM7rL9UiSdZyMmhjKr2vFthqmsdTYuSvFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3c49d7ed835c1ce9c90f91cb361658ee064e6ad535ab34c5d52b2f3c33b7d3c","last_reissued_at":"2026-05-18T00:03:27.458815Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:27.458815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.04642","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n/Ux/7fnNh5qyCGkOij0JQyH/dgurLTh9X07lqD+Mg0vYL4y4RxHL2YZwGLutJ9AWIGPSfix1u8G4gU2pC+jDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:54:55.111562Z"},"content_sha256":"7ac5230fa64cdbf39d55cf6740c22cb2c91635e75e7c3a171b992fc6583d9252","schema_version":"1.0","event_id":"sha256:7ac5230fa64cdbf39d55cf6740c22cb2c91635e75e7c3a171b992fc6583d9252"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6PCJ27WYGXA45HEQ7EOLGYLFR3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating Imitation Learning with Predictive Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Ching-An Cheng, Evangelos A. Theodorou, Xinyan Yan","submitted_at":"2018-06-12T16:55:06Z","abstract_excerpt":"Sample efficiency is critical in solving real-world reinforcement learning problems, where agent-environment interactions can be costly. Imitation learning from expert advice has proved to be an effective strategy for reducing the number of interactions required to train a policy. Online imitation learning, which interleaves policy evaluation and policy optimization, is a particularly effective technique with provable performance guarantees. In this work, we seek to further accelerate the convergence rate of online imitation learning, thereby making it more sample efficient. We propose two mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04642","kind":"arxiv","version":4},"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":"2026-05-18T00:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ErpX/+VmEkhtnGJx2kyRMiABJ4LNDhkfQQOjMN3q0v0PBKiDbLdPrSbKzEC9i0pK6jHj4FmY7cyZfQ0nXA5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:54:55.112224Z"},"content_sha256":"725d55ea6c902eba3ce655caa8617888427ae3155e947fbc88fe4f07be8059fc","schema_version":"1.0","event_id":"sha256:725d55ea6c902eba3ce655caa8617888427ae3155e947fbc88fe4f07be8059fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6PCJ27WYGXA45HEQ7EOLGYLFR3/bundle.json","state_url":"https://pith.science/pith/6PCJ27WYGXA45HEQ7EOLGYLFR3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6PCJ27WYGXA45HEQ7EOLGYLFR3/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":"2026-05-27T02:54:55Z","links":{"resolver":"https://pith.science/pith/6PCJ27WYGXA45HEQ7EOLGYLFR3","bundle":"https://pith.science/pith/6PCJ27WYGXA45HEQ7EOLGYLFR3/bundle.json","state":"https://pith.science/pith/6PCJ27WYGXA45HEQ7EOLGYLFR3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6PCJ27WYGXA45HEQ7EOLGYLFR3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6PCJ27WYGXA45HEQ7EOLGYLFR3","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":"4ea1353d92a52b81c3eabe1534744857ab97f18409f249c9daaa2f518564a814","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-12T16:55:06Z","title_canon_sha256":"9d777e759b4ef471487250305975f28f375d808bc95a1a81f1ddf8be3c7599ec"},"schema_version":"1.0","source":{"id":"1806.04642","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04642","created_at":"2026-05-18T00:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04642v4","created_at":"2026-05-18T00:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04642","created_at":"2026-05-18T00:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"6PCJ27WYGXA4","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"6PCJ27WYGXA45HEQ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"6PCJ27WY","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:725d55ea6c902eba3ce655caa8617888427ae3155e947fbc88fe4f07be8059fc","target":"graph","created_at":"2026-05-18T00:03:27Z","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":"Sample efficiency is critical in solving real-world reinforcement learning problems, where agent-environment interactions can be costly. Imitation learning from expert advice has proved to be an effective strategy for reducing the number of interactions required to train a policy. Online imitation learning, which interleaves policy evaluation and policy optimization, is a particularly effective technique with provable performance guarantees. In this work, we seek to further accelerate the convergence rate of online imitation learning, thereby making it more sample efficient. We propose two mod","authors_text":"Byron Boots, Ching-An Cheng, Evangelos A. Theodorou, Xinyan Yan","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-12T16:55:06Z","title":"Accelerating Imitation Learning with Predictive Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04642","kind":"arxiv","version":4},"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":"sha256:7ac5230fa64cdbf39d55cf6740c22cb2c91635e75e7c3a171b992fc6583d9252","target":"record","created_at":"2026-05-18T00:03:27Z","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":"4ea1353d92a52b81c3eabe1534744857ab97f18409f249c9daaa2f518564a814","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-12T16:55:06Z","title_canon_sha256":"9d777e759b4ef471487250305975f28f375d808bc95a1a81f1ddf8be3c7599ec"},"schema_version":"1.0","source":{"id":"1806.04642","kind":"arxiv","version":4}},"canonical_sha256":"f3c49d7ed835c1ce9c90f91cb361658ee064e6ad535ab34c5d52b2f3c33b7d3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3c49d7ed835c1ce9c90f91cb361658ee064e6ad535ab34c5d52b2f3c33b7d3c","first_computed_at":"2026-05-18T00:03:27.458815Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:27.458815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qtbkZouuy9LisoVtbu2IqWSgu9Vka3M62kBKAZCAjTgPP0WzW+XbM7rL9UiSdZyMmhjKr2vFthqmsdTYuSvFBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:27.459213Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.04642","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ac5230fa64cdbf39d55cf6740c22cb2c91635e75e7c3a171b992fc6583d9252","sha256:725d55ea6c902eba3ce655caa8617888427ae3155e947fbc88fe4f07be8059fc"],"state_sha256":"d9b82237c8aff945244e1e518f6f8ed7036ef263a6848eaecef1726238fbcb33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g5j2Qe6jCyHuwrdFkUDNKuvEpdl3lOtGS0dAZjMkyQK/DaWoJttmvA+R8LfR5vFFWge+/vzsZFbx2X0lEbxiBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T02:54:55.115692Z","bundle_sha256":"c1791350bf9b323568e2debf2d9625f7b3c684a16bcf952096280f81785dbae9"}}