{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OTMW4C5CHOJB2GH6LGW2YF75UH","short_pith_number":"pith:OTMW4C5C","schema_version":"1.0","canonical_sha256":"74d96e0ba23b921d18fe59adac17fda1cd466ddcf5c8a51e5cba59aae27f4bad","source":{"kind":"arxiv","id":"1709.04083","version":2},"attestation_state":"computed","paper":{"title":"Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gabriel V. de la Cruz Jr, Matthew E. Taylor, Yunshu Du","submitted_at":"2017-09-12T23:17:45Z","abstract_excerpt":"Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using a deep neural network as its function approximator and by learning directly from raw images. A drawback of using raw images is that deep RL must learn the state feature representation from the raw images in addition to learning a policy. As a result, deep RL can require a prohibitively large amount of training time and data to reach reasonable performance, making it difficult to use deep RL in real-world applications, especially when data is expensive. In this work, we speed up training"},"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":"1709.04083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-12T23:17:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"352e79d8a3e4c78721f51b4387f10ade41aa8939b1dfc70e060a6de949536043","abstract_canon_sha256":"e2b9cc1da42aa517a3d1ceb73c9f93ef0abbfe23b12308739899fe5e2355c9c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:17.962185Z","signature_b64":"pBsyVeopUh+gE47ty1PsUlXPEho+IPeSQN5Dr0wwUj5NKw8+vOzTAk2Sc4gW5ct9VbS0gfZvZgAMBKrdXy0pAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74d96e0ba23b921d18fe59adac17fda1cd466ddcf5c8a51e5cba59aae27f4bad","last_reissued_at":"2026-05-17T23:49:17.961708Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:17.961708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gabriel V. de la Cruz Jr, Matthew E. Taylor, Yunshu Du","submitted_at":"2017-09-12T23:17:45Z","abstract_excerpt":"Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using a deep neural network as its function approximator and by learning directly from raw images. A drawback of using raw images is that deep RL must learn the state feature representation from the raw images in addition to learning a policy. As a result, deep RL can require a prohibitively large amount of training time and data to reach reasonable performance, making it difficult to use deep RL in real-world applications, especially when data is expensive. In this work, we speed up training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04083","kind":"arxiv","version":2},"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":"1709.04083","created_at":"2026-05-17T23:49:17.961785+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.04083v2","created_at":"2026-05-17T23:49:17.961785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04083","created_at":"2026-05-17T23:49:17.961785+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTMW4C5CHOJB","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTMW4C5CHOJB2GH6","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTMW4C5C","created_at":"2026-05-18T12:31:34.259226+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/OTMW4C5CHOJB2GH6LGW2YF75UH","json":"https://pith.science/pith/OTMW4C5CHOJB2GH6LGW2YF75UH.json","graph_json":"https://pith.science/api/pith-number/OTMW4C5CHOJB2GH6LGW2YF75UH/graph.json","events_json":"https://pith.science/api/pith-number/OTMW4C5CHOJB2GH6LGW2YF75UH/events.json","paper":"https://pith.science/paper/OTMW4C5C"},"agent_actions":{"view_html":"https://pith.science/pith/OTMW4C5CHOJB2GH6LGW2YF75UH","download_json":"https://pith.science/pith/OTMW4C5CHOJB2GH6LGW2YF75UH.json","view_paper":"https://pith.science/paper/OTMW4C5C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.04083&json=true","fetch_graph":"https://pith.science/api/pith-number/OTMW4C5CHOJB2GH6LGW2YF75UH/graph.json","fetch_events":"https://pith.science/api/pith-number/OTMW4C5CHOJB2GH6LGW2YF75UH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTMW4C5CHOJB2GH6LGW2YF75UH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTMW4C5CHOJB2GH6LGW2YF75UH/action/storage_attestation","attest_author":"https://pith.science/pith/OTMW4C5CHOJB2GH6LGW2YF75UH/action/author_attestation","sign_citation":"https://pith.science/pith/OTMW4C5CHOJB2GH6LGW2YF75UH/action/citation_signature","submit_replication":"https://pith.science/pith/OTMW4C5CHOJB2GH6LGW2YF75UH/action/replication_record"}},"created_at":"2026-05-17T23:49:17.961785+00:00","updated_at":"2026-05-17T23:49:17.961785+00:00"}