{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JMSWJQRMHEVAC6WZONA3NKJA5M","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"23b159758cd98567b064f694e01594aa43046c443d0567d363d6c14ae3b70a21","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T17:21:43Z","title_canon_sha256":"aff9553bf4d4ca3b232f316cfa74869ccf9943375566c45eb6c300d2cde48d6c"},"schema_version":"1.0","source":{"id":"2006.16210","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.16210","created_at":"2026-07-05T01:45:43Z"},{"alias_kind":"arxiv_version","alias_value":"2006.16210v2","created_at":"2026-07-05T01:45:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16210","created_at":"2026-07-05T01:45:43Z"},{"alias_kind":"pith_short_12","alias_value":"JMSWJQRMHEVA","created_at":"2026-07-05T01:45:43Z"},{"alias_kind":"pith_short_16","alias_value":"JMSWJQRMHEVAC6WZ","created_at":"2026-07-05T01:45:43Z"},{"alias_kind":"pith_short_8","alias_value":"JMSWJQRM","created_at":"2026-07-05T01:45:43Z"}],"graph_snapshots":[{"event_id":"sha256:ecbe1bd06a06ccda12d08734a52c5cd48efee8fabd9ccc53cbdb0f11615544e9","target":"graph","created_at":"2026-07-05T01:45:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.16210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Finale Doshi-Velez, Jianzhun Du, Joseph Futoma","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T17:21:43Z","title":"Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16210","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f823ea994bd9ee67f6b7ea05ee3d0dadc42e5024ef8fbdd573b8bc11451093e8","target":"record","created_at":"2026-07-05T01:45:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"23b159758cd98567b064f694e01594aa43046c443d0567d363d6c14ae3b70a21","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T17:21:43Z","title_canon_sha256":"aff9553bf4d4ca3b232f316cfa74869ccf9943375566c45eb6c300d2cde48d6c"},"schema_version":"1.0","source":{"id":"2006.16210","kind":"arxiv","version":2}},"canonical_sha256":"4b2564c22c392a017ad97341b6a920eb1d37ad2d337d378597057aec6dc9a826","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b2564c22c392a017ad97341b6a920eb1d37ad2d337d378597057aec6dc9a826","first_computed_at":"2026-07-05T01:45:43.829379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:43.829379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AdzOHgSZNWMK2kUtFvsLZGSjZlu4KlOoXbRI2fcBklSGEo4suaZtSnbzR6dwluWLDKLoCGgiqjpzguQBe3WaDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:43.829851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.16210","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f823ea994bd9ee67f6b7ea05ee3d0dadc42e5024ef8fbdd573b8bc11451093e8","sha256:ecbe1bd06a06ccda12d08734a52c5cd48efee8fabd9ccc53cbdb0f11615544e9"],"state_sha256":"f9f4b1ba67db44c2f035440cae228ba1048ca2a19ffc41e36275d04e866bfb3b"}