{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D7M55WX6PDRZH5G3LF4IKSDPAU","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":"cefbfb194fb59f9ffb6785953ecd846a9f2a4ad699adbfea6fa8242ed954e722","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T12:05:20Z","title_canon_sha256":"3943bee0737e4f5b8f63a003895789e05104b1ee6f330a409090a036a738bc11"},"schema_version":"1.0","source":{"id":"2405.18100","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18100","created_at":"2026-07-05T10:52:12Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18100v3","created_at":"2026-07-05T10:52:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18100","created_at":"2026-07-05T10:52:12Z"},{"alias_kind":"pith_short_12","alias_value":"D7M55WX6PDRZ","created_at":"2026-07-05T10:52:12Z"},{"alias_kind":"pith_short_16","alias_value":"D7M55WX6PDRZH5G3","created_at":"2026-07-05T10:52:12Z"},{"alias_kind":"pith_short_8","alias_value":"D7M55WX6","created_at":"2026-07-05T10:52:12Z"}],"graph_snapshots":[{"event_id":"sha256:70d2239abf23f238a708d3415d93dc24efcb10bafc736cf70046f243368aa15b","target":"graph","created_at":"2026-07-05T10:52:12Z","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/2405.18100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has traditionally focused on learning state-dependent policies to solve optimal control problems in a closed-loop fashion. In this work, we introduce the paradigm of open-loop reinforcement learning where a fixed action sequence is learned instead. We present three new algorithms: one robust model-based method and two sample-efficient model-free methods. Rather than basing our algorithms on Bellman's equation from dynamic programming, our work builds on Pontryagin's principle from the theory of open-loop optimal control. We provide convergence guarantees and evaluate all","authors_text":"Claire Vernade, Michael Muehlebach, Onno Eberhard","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T12:05:20Z","title":"A Pontryagin Perspective on Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18100","kind":"arxiv","version":3},"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:aef592792d0ad2f3c90b3c0e0ef8775b9ac6bf9ddd69a0ed5a96d222809fc226","target":"record","created_at":"2026-07-05T10:52:12Z","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":"cefbfb194fb59f9ffb6785953ecd846a9f2a4ad699adbfea6fa8242ed954e722","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T12:05:20Z","title_canon_sha256":"3943bee0737e4f5b8f63a003895789e05104b1ee6f330a409090a036a738bc11"},"schema_version":"1.0","source":{"id":"2405.18100","kind":"arxiv","version":3}},"canonical_sha256":"1fd9dedafe78e393f4db597885486f050452550146f99834144a46078c8e95d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fd9dedafe78e393f4db597885486f050452550146f99834144a46078c8e95d7","first_computed_at":"2026-07-05T10:52:12.060942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:12.060942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PzkchlCCTk13VJK88zE3tp5nlycEVvvVG/hvmyHc0PT5ZyRrwR2p1y/+kHMomuiquEJk0mTxuR4AOJt5qel6BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:12.061431Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18100","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aef592792d0ad2f3c90b3c0e0ef8775b9ac6bf9ddd69a0ed5a96d222809fc226","sha256:70d2239abf23f238a708d3415d93dc24efcb10bafc736cf70046f243368aa15b"],"state_sha256":"12f0a88be7d4afd64f67706e28369cf72d30945da652082ee585cc6e56dd511e"}