{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:L7BO5U2SDCYEG3UW27U5SUV6Q3","short_pith_number":"pith:L7BO5U2S","schema_version":"1.0","canonical_sha256":"5fc2eed35218b0436e96d7e9d952be86fe832fec0af8f579596d201da9d22c57","source":{"kind":"arxiv","id":"1811.03853","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1811.03853","created_at":"2026-05-18T00:01:11.790240+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.03853v1","created_at":"2026-05-18T00:01:11.790240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03853","created_at":"2026-05-18T00:01:11.790240+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7BO5U2SDCYE","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7BO5U2SDCYEG3UW","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7BO5U2S","created_at":"2026-05-18T12:32:33.847187+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/L7BO5U2SDCYEG3UW27U5SUV6Q3","json":"https://pith.science/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3.json","graph_json":"https://pith.science/api/pith-number/L7BO5U2SDCYEG3UW27U5SUV6Q3/graph.json","events_json":"https://pith.science/api/pith-number/L7BO5U2SDCYEG3UW27U5SUV6Q3/events.json","paper":"https://pith.science/paper/L7BO5U2S"},"agent_actions":{"view_html":"https://pith.science/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3","download_json":"https://pith.science/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3.json","view_paper":"https://pith.science/paper/L7BO5U2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.03853&json=true","fetch_graph":"https://pith.science/api/pith-number/L7BO5U2SDCYEG3UW27U5SUV6Q3/graph.json","fetch_events":"https://pith.science/api/pith-number/L7BO5U2SDCYEG3UW27U5SUV6Q3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3/action/storage_attestation","attest_author":"https://pith.science/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3/action/author_attestation","sign_citation":"https://pith.science/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3/action/citation_signature","submit_replication":"https://pith.science/pith/L7BO5U2SDCYEG3UW27U5SUV6Q3/action/replication_record"}},"created_at":"2026-05-18T00:01:11.790240+00:00","updated_at":"2026-05-18T00:01:11.790240+00:00"}