{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JMSWJQRMHEVAC6WZONA3NKJA5M","short_pith_number":"pith:JMSWJQRM","schema_version":"1.0","canonical_sha256":"4b2564c22c392a017ad97341b6a920eb1d37ad2d337d378597057aec6dc9a826","source":{"kind":"arxiv","id":"2006.16210","version":2},"attestation_state":"computed","paper":{"title":"Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Finale Doshi-Velez, Jianzhun Du, Joseph Futoma","submitted_at":"2020-06-29T17:21:43Z","abstract_excerpt":"We present two elegant solutions for modeling continuous-time dynamics, in a novel model-based reinforcement learning (RL) framework for semi-Markov decision processes (SMDPs), using neural ordinary differential equations (ODEs). Our models accurately characterize continuous-time dynamics and enable us to develop high-performing policies using a small amount of data. We also develop a model-based approach for optimizing time schedules to reduce interaction rates with the environment while maintaining the near-optimal performance, which is not possible for model-free methods. We experimentally "},"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":"2006.16210","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T17:21:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"aff9553bf4d4ca3b232f316cfa74869ccf9943375566c45eb6c300d2cde48d6c","abstract_canon_sha256":"23b159758cd98567b064f694e01594aa43046c443d0567d363d6c14ae3b70a21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:43.829851Z","signature_b64":"AdzOHgSZNWMK2kUtFvsLZGSjZlu4KlOoXbRI2fcBklSGEo4suaZtSnbzR6dwluWLDKLoCGgiqjpzguQBe3WaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b2564c22c392a017ad97341b6a920eb1d37ad2d337d378597057aec6dc9a826","last_reissued_at":"2026-07-05T01:45:43.829379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:43.829379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Finale Doshi-Velez, Jianzhun Du, Joseph Futoma","submitted_at":"2020-06-29T17:21:43Z","abstract_excerpt":"We present two elegant solutions for modeling continuous-time dynamics, in a novel model-based reinforcement learning (RL) framework for semi-Markov decision processes (SMDPs), using neural ordinary differential equations (ODEs). Our models accurately characterize continuous-time dynamics and enable us to develop high-performing policies using a small amount of data. We also develop a model-based approach for optimizing time schedules to reduce interaction rates with the environment while maintaining the near-optimal performance, which is not possible for model-free methods. We experimentally "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16210","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.16210/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2006.16210","created_at":"2026-07-05T01:45:43.829441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.16210v2","created_at":"2026-07-05T01:45:43.829441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16210","created_at":"2026-07-05T01:45:43.829441+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMSWJQRMHEVA","created_at":"2026-07-05T01:45:43.829441+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMSWJQRMHEVAC6WZ","created_at":"2026-07-05T01:45:43.829441+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMSWJQRM","created_at":"2026-07-05T01:45:43.829441+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/JMSWJQRMHEVAC6WZONA3NKJA5M","json":"https://pith.science/pith/JMSWJQRMHEVAC6WZONA3NKJA5M.json","graph_json":"https://pith.science/api/pith-number/JMSWJQRMHEVAC6WZONA3NKJA5M/graph.json","events_json":"https://pith.science/api/pith-number/JMSWJQRMHEVAC6WZONA3NKJA5M/events.json","paper":"https://pith.science/paper/JMSWJQRM"},"agent_actions":{"view_html":"https://pith.science/pith/JMSWJQRMHEVAC6WZONA3NKJA5M","download_json":"https://pith.science/pith/JMSWJQRMHEVAC6WZONA3NKJA5M.json","view_paper":"https://pith.science/paper/JMSWJQRM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.16210&json=true","fetch_graph":"https://pith.science/api/pith-number/JMSWJQRMHEVAC6WZONA3NKJA5M/graph.json","fetch_events":"https://pith.science/api/pith-number/JMSWJQRMHEVAC6WZONA3NKJA5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMSWJQRMHEVAC6WZONA3NKJA5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMSWJQRMHEVAC6WZONA3NKJA5M/action/storage_attestation","attest_author":"https://pith.science/pith/JMSWJQRMHEVAC6WZONA3NKJA5M/action/author_attestation","sign_citation":"https://pith.science/pith/JMSWJQRMHEVAC6WZONA3NKJA5M/action/citation_signature","submit_replication":"https://pith.science/pith/JMSWJQRMHEVAC6WZONA3NKJA5M/action/replication_record"}},"created_at":"2026-07-05T01:45:43.829441+00:00","updated_at":"2026-07-05T01:45:43.829441+00:00"}