{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BUXOISRLTU3BKY62AFV3RODSWR","short_pith_number":"pith:BUXOISRL","schema_version":"1.0","canonical_sha256":"0d2ee44a2b9d361563da016bb8b872b47579eddff8754682cb66eec29d19e41a","source":{"kind":"arxiv","id":"1907.03116","version":1},"attestation_state":"computed","paper":{"title":"Intrinsic Motivation Driven Intuitive Physics Learning using Deep Reinforcement Learning with Intrinsic Reward Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jaewon Choi, Sung-Eui Yoon","submitted_at":"2019-07-06T11:08:17Z","abstract_excerpt":"At an early age, human infants are able to learn and build a model of the world very quickly by constantly observing and interacting with objects around them. One of the most fundamental intuitions human infants acquire is intuitive physics. Human infants learn and develop these models, which later serve as prior knowledge for further learning. Inspired by such behaviors exhibited by human infants, we introduce a graphical physics network integrated with deep reinforcement learning. Specifically, we introduce an intrinsic reward normalization method that allows our agent to efficiently choose "},"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":"1907.03116","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-06T11:08:17Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"eb950c3a19b150f30375c17668930f8a79c3a68c4d74d6d1211a8227f5b20300","abstract_canon_sha256":"d8f0951186397eeacdaea0399861b66f09930e971a170b20a611cb76be9bef03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:18.894993Z","signature_b64":"7C/vJ4F9JzWr61NI4kvzWZHZ+bmLnsEyxeK/HGboZA/q7z2WHyIN3JsGRh55GgdeSWiIpn58KPxDyczgNr8oAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d2ee44a2b9d361563da016bb8b872b47579eddff8754682cb66eec29d19e41a","last_reissued_at":"2026-05-17T23:41:18.894255Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:18.894255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intrinsic Motivation Driven Intuitive Physics Learning using Deep Reinforcement Learning with Intrinsic Reward Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jaewon Choi, Sung-Eui Yoon","submitted_at":"2019-07-06T11:08:17Z","abstract_excerpt":"At an early age, human infants are able to learn and build a model of the world very quickly by constantly observing and interacting with objects around them. One of the most fundamental intuitions human infants acquire is intuitive physics. Human infants learn and develop these models, which later serve as prior knowledge for further learning. Inspired by such behaviors exhibited by human infants, we introduce a graphical physics network integrated with deep reinforcement learning. Specifically, we introduce an intrinsic reward normalization method that allows our agent to efficiently choose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03116","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":"1907.03116","created_at":"2026-05-17T23:41:18.894397+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.03116v1","created_at":"2026-05-17T23:41:18.894397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03116","created_at":"2026-05-17T23:41:18.894397+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUXOISRLTU3B","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUXOISRLTU3BKY62","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUXOISRL","created_at":"2026-05-18T12:33:12.712433+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/BUXOISRLTU3BKY62AFV3RODSWR","json":"https://pith.science/pith/BUXOISRLTU3BKY62AFV3RODSWR.json","graph_json":"https://pith.science/api/pith-number/BUXOISRLTU3BKY62AFV3RODSWR/graph.json","events_json":"https://pith.science/api/pith-number/BUXOISRLTU3BKY62AFV3RODSWR/events.json","paper":"https://pith.science/paper/BUXOISRL"},"agent_actions":{"view_html":"https://pith.science/pith/BUXOISRLTU3BKY62AFV3RODSWR","download_json":"https://pith.science/pith/BUXOISRLTU3BKY62AFV3RODSWR.json","view_paper":"https://pith.science/paper/BUXOISRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.03116&json=true","fetch_graph":"https://pith.science/api/pith-number/BUXOISRLTU3BKY62AFV3RODSWR/graph.json","fetch_events":"https://pith.science/api/pith-number/BUXOISRLTU3BKY62AFV3RODSWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUXOISRLTU3BKY62AFV3RODSWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUXOISRLTU3BKY62AFV3RODSWR/action/storage_attestation","attest_author":"https://pith.science/pith/BUXOISRLTU3BKY62AFV3RODSWR/action/author_attestation","sign_citation":"https://pith.science/pith/BUXOISRLTU3BKY62AFV3RODSWR/action/citation_signature","submit_replication":"https://pith.science/pith/BUXOISRLTU3BKY62AFV3RODSWR/action/replication_record"}},"created_at":"2026-05-17T23:41:18.894397+00:00","updated_at":"2026-05-17T23:41:18.894397+00:00"}