{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:U4XDZQNHXGWF5E3UAMXGFCI2RU","short_pith_number":"pith:U4XDZQNH","schema_version":"1.0","canonical_sha256":"a72e3cc1a7b9ac5e9374032e62891a8d3ec6aa305f8f9c21c5f033be81b98f5e","source":{"kind":"arxiv","id":"1812.11240","version":2},"attestation_state":"computed","paper":{"title":"Dynamic Planning Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Miriam Capretz, Norman Tasfi","submitted_at":"2018-12-28T22:37:30Z","abstract_excerpt":"We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct plans using a learned state-transition model by selecting and traversing between simulated states and actions to maximize information before acting. In contrast to model-free methods, model-based planning lets the agent efficiently test action hypotheses without performing costly trial-and-error in the environment. DPN learns to efficiently form plans by expanding a single actio"},"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":"1812.11240","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-28T22:37:30Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"ea122248531d87cca6785fdda3071f95afe8fc2e78b4b8af75b0df29b8eb853c","abstract_canon_sha256":"7715218b4954153bc12ed0b8c5e076ae72349da9eb04156e0dc1a8be89f82e85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:53.235232Z","signature_b64":"X3vJcEr55WA19PaZkwHKi0vz+R08Y7ZJC67O8+Gga+xRnFdgGT8UvnfHq41dO/Qh/Z1FRMbFGTbK09/zwlG/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a72e3cc1a7b9ac5e9374032e62891a8d3ec6aa305f8f9c21c5f033be81b98f5e","last_reissued_at":"2026-05-17T23:54:53.234756Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:53.234756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Planning Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Miriam Capretz, Norman Tasfi","submitted_at":"2018-12-28T22:37:30Z","abstract_excerpt":"We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct plans using a learned state-transition model by selecting and traversing between simulated states and actions to maximize information before acting. In contrast to model-free methods, model-based planning lets the agent efficiently test action hypotheses without performing costly trial-and-error in the environment. DPN learns to efficiently form plans by expanding a single actio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11240","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":"1812.11240","created_at":"2026-05-17T23:54:53.234829+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.11240v2","created_at":"2026-05-17T23:54:53.234829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11240","created_at":"2026-05-17T23:54:53.234829+00:00"},{"alias_kind":"pith_short_12","alias_value":"U4XDZQNHXGWF","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"U4XDZQNHXGWF5E3U","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"U4XDZQNH","created_at":"2026-05-18T12:32:56.356000+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/U4XDZQNHXGWF5E3UAMXGFCI2RU","json":"https://pith.science/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU.json","graph_json":"https://pith.science/api/pith-number/U4XDZQNHXGWF5E3UAMXGFCI2RU/graph.json","events_json":"https://pith.science/api/pith-number/U4XDZQNHXGWF5E3UAMXGFCI2RU/events.json","paper":"https://pith.science/paper/U4XDZQNH"},"agent_actions":{"view_html":"https://pith.science/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU","download_json":"https://pith.science/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU.json","view_paper":"https://pith.science/paper/U4XDZQNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.11240&json=true","fetch_graph":"https://pith.science/api/pith-number/U4XDZQNHXGWF5E3UAMXGFCI2RU/graph.json","fetch_events":"https://pith.science/api/pith-number/U4XDZQNHXGWF5E3UAMXGFCI2RU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU/action/storage_attestation","attest_author":"https://pith.science/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU/action/author_attestation","sign_citation":"https://pith.science/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU/action/citation_signature","submit_replication":"https://pith.science/pith/U4XDZQNHXGWF5E3UAMXGFCI2RU/action/replication_record"}},"created_at":"2026-05-17T23:54:53.234829+00:00","updated_at":"2026-05-17T23:54:53.234829+00:00"}