{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WM5PTMFP4YXFJQ2QQPTGZ4JGVW","short_pith_number":"pith:WM5PTMFP","schema_version":"1.0","canonical_sha256":"b33af9b0afe62e54c35083e66cf126adbe1c2b493a08f9d2a18f3372501d1500","source":{"kind":"arxiv","id":"1703.06692","version":3},"attestation_state":"computed","paper":{"title":"QMDP-Net: Deep Learning for Planning under Partial Observability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.AI","authors_text":"David Hsu, Peter Karkus, Wee Sun Lee","submitted_at":"2017-03-20T11:44:00Z","abstract_excerpt":"This paper introduces the QMDP-net, a neural network architecture for planning under partial observability. The QMDP-net combines the strengths of model-free learning and model-based planning. It is a recurrent policy network, but it represents a policy for a parameterized set of tasks by connecting a model with a planning algorithm that solves the model, thus embedding the solution structure of planning in a network learning architecture. The QMDP-net is fully differentiable and allows for end-to-end training. We train a QMDP-net on different tasks so that it can generalize to new ones in the"},"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":"1703.06692","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-20T11:44:00Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"b7395eb7401e4fc9aaa52cd6169f981f07241ba4741b5660b8c78d48682e800e","abstract_canon_sha256":"6083d708094c711d2d94cf17b8da6a05da4543caeb66742cedc645976f6e7fa2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:28.908685Z","signature_b64":"/s+JSWtct3MVbBCmDTQV2NzlTSGgMnfxHV1AHbY9AhiRRpCYumypt8dkvutsYCQgDK5rjy8cbAs9J2gOWpKgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b33af9b0afe62e54c35083e66cf126adbe1c2b493a08f9d2a18f3372501d1500","last_reissued_at":"2026-05-18T00:31:28.908069Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:28.908069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QMDP-Net: Deep Learning for Planning under Partial Observability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.AI","authors_text":"David Hsu, Peter Karkus, Wee Sun Lee","submitted_at":"2017-03-20T11:44:00Z","abstract_excerpt":"This paper introduces the QMDP-net, a neural network architecture for planning under partial observability. The QMDP-net combines the strengths of model-free learning and model-based planning. It is a recurrent policy network, but it represents a policy for a parameterized set of tasks by connecting a model with a planning algorithm that solves the model, thus embedding the solution structure of planning in a network learning architecture. The QMDP-net is fully differentiable and allows for end-to-end training. We train a QMDP-net on different tasks so that it can generalize to new ones in the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06692","kind":"arxiv","version":3},"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":"1703.06692","created_at":"2026-05-18T00:31:28.908164+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.06692v3","created_at":"2026-05-18T00:31:28.908164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06692","created_at":"2026-05-18T00:31:28.908164+00:00"},{"alias_kind":"pith_short_12","alias_value":"WM5PTMFP4YXF","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WM5PTMFP4YXFJQ2Q","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WM5PTMFP","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02112","citing_title":"An adaptive variance estimator for relative sparsity","ref_index":231,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW","json":"https://pith.science/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW.json","graph_json":"https://pith.science/api/pith-number/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/graph.json","events_json":"https://pith.science/api/pith-number/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/events.json","paper":"https://pith.science/paper/WM5PTMFP"},"agent_actions":{"view_html":"https://pith.science/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW","download_json":"https://pith.science/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW.json","view_paper":"https://pith.science/paper/WM5PTMFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.06692&json=true","fetch_graph":"https://pith.science/api/pith-number/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/graph.json","fetch_events":"https://pith.science/api/pith-number/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/action/storage_attestation","attest_author":"https://pith.science/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/action/author_attestation","sign_citation":"https://pith.science/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/action/citation_signature","submit_replication":"https://pith.science/pith/WM5PTMFP4YXFJQ2QQPTGZ4JGVW/action/replication_record"}},"created_at":"2026-05-18T00:31:28.908164+00:00","updated_at":"2026-05-18T00:31:28.908164+00:00"}