{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ONQCAF2TX7GCNLYJGAFRRQXEBL","short_pith_number":"pith:ONQCAF2T","schema_version":"1.0","canonical_sha256":"7360201753bfcc26af09300b18c2e40ae6bac2d9874eaba5e971b7db68e6ea99","source":{"kind":"arxiv","id":"1907.04902","version":1},"attestation_state":"computed","paper":{"title":"Interpretable Dynamics Models for Data-Efficient Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carl Henrik Ek, Clemens Otte, Markus Kaiser, Thomas Runkler","submitted_at":"2019-07-10T19:50:45Z","abstract_excerpt":"In this paper, we present a Bayesian view on model-based reinforcement learning. We use expert knowledge to impose structure on the transition model and present an efficient learning scheme based on variational inference. This scheme is applied to a heteroskedastic and bimodal benchmark problem on which we compare our results to NFQ and show how our approach yields human-interpretable insight about the underlying dynamics while also increasing data-efficiency."},"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":"1907.04902","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-10T19:50:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"95c6edc281a9b754bbff4cdb8e01ee5dabbaab677a29f884a25ed66b9db8bd4b","abstract_canon_sha256":"8a60c487c3c3dd91bd991b480493177158e1bf9915dcc36a97fb03933ba97c7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:54.617824Z","signature_b64":"dSgasp0LrITMDDP0dXCKohcAfCpBe2+eGXdrm6fPlav4QFFxrRNRtAWQcRRci1V3SvqGK26jheiQsFAQostwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7360201753bfcc26af09300b18c2e40ae6bac2d9874eaba5e971b7db68e6ea99","last_reissued_at":"2026-05-17T23:40:54.617184Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:54.617184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Dynamics Models for Data-Efficient Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carl Henrik Ek, Clemens Otte, Markus Kaiser, Thomas Runkler","submitted_at":"2019-07-10T19:50:45Z","abstract_excerpt":"In this paper, we present a Bayesian view on model-based reinforcement learning. We use expert knowledge to impose structure on the transition model and present an efficient learning scheme based on variational inference. This scheme is applied to a heteroskedastic and bimodal benchmark problem on which we compare our results to NFQ and show how our approach yields human-interpretable insight about the underlying dynamics while also increasing data-efficiency."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04902","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":"1907.04902","created_at":"2026-05-17T23:40:54.617286+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.04902v1","created_at":"2026-05-17T23:40:54.617286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04902","created_at":"2026-05-17T23:40:54.617286+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONQCAF2TX7GC","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONQCAF2TX7GCNLYJ","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONQCAF2T","created_at":"2026-05-18T12:33:24.271573+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/ONQCAF2TX7GCNLYJGAFRRQXEBL","json":"https://pith.science/pith/ONQCAF2TX7GCNLYJGAFRRQXEBL.json","graph_json":"https://pith.science/api/pith-number/ONQCAF2TX7GCNLYJGAFRRQXEBL/graph.json","events_json":"https://pith.science/api/pith-number/ONQCAF2TX7GCNLYJGAFRRQXEBL/events.json","paper":"https://pith.science/paper/ONQCAF2T"},"agent_actions":{"view_html":"https://pith.science/pith/ONQCAF2TX7GCNLYJGAFRRQXEBL","download_json":"https://pith.science/pith/ONQCAF2TX7GCNLYJGAFRRQXEBL.json","view_paper":"https://pith.science/paper/ONQCAF2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.04902&json=true","fetch_graph":"https://pith.science/api/pith-number/ONQCAF2TX7GCNLYJGAFRRQXEBL/graph.json","fetch_events":"https://pith.science/api/pith-number/ONQCAF2TX7GCNLYJGAFRRQXEBL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONQCAF2TX7GCNLYJGAFRRQXEBL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONQCAF2TX7GCNLYJGAFRRQXEBL/action/storage_attestation","attest_author":"https://pith.science/pith/ONQCAF2TX7GCNLYJGAFRRQXEBL/action/author_attestation","sign_citation":"https://pith.science/pith/ONQCAF2TX7GCNLYJGAFRRQXEBL/action/citation_signature","submit_replication":"https://pith.science/pith/ONQCAF2TX7GCNLYJGAFRRQXEBL/action/replication_record"}},"created_at":"2026-05-17T23:40:54.617286+00:00","updated_at":"2026-05-17T23:40:54.617286+00:00"}