{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:L7BO5U2SDCYEG3UW27U5SUV6Q3","short_pith_number":"pith:L7BO5U2S","canonical_record":{"source":{"id":"1811.03853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T10:34:53Z","cross_cats_sorted":["cs.AI","cs.SY"],"title_canon_sha256":"d71a20563ac9fc53f3358509245f26623d0927f097b9f5328cfbc9c7ac786898","abstract_canon_sha256":"2fb2cbad026b0785e22895c8c233c6c06d5346000588662823b204720494b0ac"},"schema_version":"1.0"},"canonical_sha256":"5fc2eed35218b0436e96d7e9d952be86fe832fec0af8f579596d201da9d22c57","source":{"kind":"arxiv","id":"1811.03853","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03853","created_at":"2026-05-18T00:01:11Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03853v1","created_at":"2026-05-18T00:01:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03853","created_at":"2026-05-18T00:01:11Z"},{"alias_kind":"pith_short_12","alias_value":"L7BO5U2SDCYE","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"L7BO5U2SDCYEG3UW","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"L7BO5U2S","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:L7BO5U2SDCYEG3UW27U5SUV6Q3","target":"record","payload":{"canonical_record":{"source":{"id":"1811.03853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T10:34:53Z","cross_cats_sorted":["cs.AI","cs.SY"],"title_canon_sha256":"d71a20563ac9fc53f3358509245f26623d0927f097b9f5328cfbc9c7ac786898","abstract_canon_sha256":"2fb2cbad026b0785e22895c8c233c6c06d5346000588662823b204720494b0ac"},"schema_version":"1.0"},"canonical_sha256":"5fc2eed35218b0436e96d7e9d952be86fe832fec0af8f579596d201da9d22c57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:11.790812Z","signature_b64":"o0ivg5SZEoIQHtQTX8Zp5jUQ1Gekf3k3zZNENonvTuh20c8v1fubX14+mWq7nC0rE3efKFhaQ9XB4lN+JHq9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fc2eed35218b0436e96d7e9d952be86fe832fec0af8f579596d201da9d22c57","last_reissued_at":"2026-05-18T00:01:11.790124Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:11.790124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.03853","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":"2026-05-18T00:01:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"21nCEzmmICFfv0ajP4nqhbhrj+HQREqCoK9qWrh6r3I5EOXcflIPWaODvfgZt14A4BOSYXNHa/DCDUfwNe0LCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T16:16:32.154778Z"},"content_sha256":"b8c34775b3626413aafd2fc6d35fcf77d47e5035b78c0f33ad232889ec26bdd6","schema_version":"1.0","event_id":"sha256:b8c34775b3626413aafd2fc6d35fcf77d47e5035b78c0f33ad232889ec26bdd6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:L7BO5U2SDCYEG3UW27U5SUV6Q3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample-Efficient Policy Learning based on Completely Behavior Cloning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY"],"primary_cat":"cs.LG","authors_text":"Ke Lu, Ling Wang, Qiming Zou, Yu Li","submitted_at":"2018-11-09T10:34:53Z","abstract_excerpt":"Direct policy search is one of the most important algorithm of reinforcement learning. However, learning from scratch needs a large amount of experience data and can be easily prone to poor local optima. In addition to that, a partially trained policy tends to perform dangerous action to agent and environment. In order to overcome these challenges, this paper proposed a policy initialization algorithm called Policy Learning based on Completely Behavior Cloning (PLCBC). PLCBC first transforms the Model Predictive Control (MPC) controller into a piecewise affine (PWA) function using multi-parame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03853","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":"2026-05-18T00:01:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DYB+R/KGr+ClvJyCOAF1oTKroekpZtaHNkj1efpErYlpxxUBUBWn+3URnb/B3ZlV46tOmO2Q+YAkeF6IOSVNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T16:16:32.155122Z"},"content_sha256":"eb113803fe9749a87a550c9db3c8116fe1c7f53a6a8521e1a0ca6494c465b2f5","schema_version":"1.0","event_id":"sha256:eb113803fe9749a87a550c9db3c8116fe1c7f53a6a8521e1a0ca6494c465b2f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3/bundle.json","state_url":"https://pith.science/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3/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":"2026-06-03T16:16:32Z","links":{"resolver":"https://pith.science/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3","bundle":"https://pith.science/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3/bundle.json","state":"https://pith.science/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:L7BO5U2SDCYEG3UW27U5SUV6Q3","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":"2fb2cbad026b0785e22895c8c233c6c06d5346000588662823b204720494b0ac","cross_cats_sorted":["cs.AI","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T10:34:53Z","title_canon_sha256":"d71a20563ac9fc53f3358509245f26623d0927f097b9f5328cfbc9c7ac786898"},"schema_version":"1.0","source":{"id":"1811.03853","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03853","created_at":"2026-05-18T00:01:11Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03853v1","created_at":"2026-05-18T00:01:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03853","created_at":"2026-05-18T00:01:11Z"},{"alias_kind":"pith_short_12","alias_value":"L7BO5U2SDCYE","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"L7BO5U2SDCYEG3UW","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"L7BO5U2S","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:eb113803fe9749a87a550c9db3c8116fe1c7f53a6a8521e1a0ca6494c465b2f5","target":"graph","created_at":"2026-05-18T00:01:11Z","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":"Direct policy search is one of the most important algorithm of reinforcement learning. However, learning from scratch needs a large amount of experience data and can be easily prone to poor local optima. In addition to that, a partially trained policy tends to perform dangerous action to agent and environment. In order to overcome these challenges, this paper proposed a policy initialization algorithm called Policy Learning based on Completely Behavior Cloning (PLCBC). PLCBC first transforms the Model Predictive Control (MPC) controller into a piecewise affine (PWA) function using multi-parame","authors_text":"Ke Lu, Ling Wang, Qiming Zou, Yu Li","cross_cats":["cs.AI","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T10:34:53Z","title":"Sample-Efficient Policy Learning based on Completely Behavior Cloning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03853","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:b8c34775b3626413aafd2fc6d35fcf77d47e5035b78c0f33ad232889ec26bdd6","target":"record","created_at":"2026-05-18T00:01:11Z","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":"2fb2cbad026b0785e22895c8c233c6c06d5346000588662823b204720494b0ac","cross_cats_sorted":["cs.AI","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T10:34:53Z","title_canon_sha256":"d71a20563ac9fc53f3358509245f26623d0927f097b9f5328cfbc9c7ac786898"},"schema_version":"1.0","source":{"id":"1811.03853","kind":"arxiv","version":1}},"canonical_sha256":"5fc2eed35218b0436e96d7e9d952be86fe832fec0af8f579596d201da9d22c57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fc2eed35218b0436e96d7e9d952be86fe832fec0af8f579596d201da9d22c57","first_computed_at":"2026-05-18T00:01:11.790124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:11.790124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o0ivg5SZEoIQHtQTX8Zp5jUQ1Gekf3k3zZNENonvTuh20c8v1fubX14+mWq7nC0rE3efKFhaQ9XB4lN+JHq9BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:11.790812Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.03853","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8c34775b3626413aafd2fc6d35fcf77d47e5035b78c0f33ad232889ec26bdd6","sha256:eb113803fe9749a87a550c9db3c8116fe1c7f53a6a8521e1a0ca6494c465b2f5"],"state_sha256":"bfb246e25f90591dee6440466c49ab148b93475c28a626b9a42c44c46d506697"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Apg9KHHrXh1NdVSuUj8YtMP+HC1jO+MxqCdvshyFuZ4CT1KjnXYWVlEultZOsK7CksAp+WBdf+tDGaVe7KkCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T16:16:32.157093Z","bundle_sha256":"599098180a54c673c9b586cd5b639407085b896ef98af59a158ef269ae03b811"}}