{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YNXJ6W76QQ436QRPRH47Z5PIBQ","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":"8b67c6f968a26ad35ad56eb2d68b956b2d11c49dd64b44c9ad1e658dffde3c81","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T10:44:20Z","title_canon_sha256":"daa9861dfe11420ae30c0fb8d50280f7bf48941aab3f57d5f789769aeadd1362"},"schema_version":"1.0","source":{"id":"2411.11457","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11457","created_at":"2026-07-05T09:36:56Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11457v1","created_at":"2026-07-05T09:36:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11457","created_at":"2026-07-05T09:36:56Z"},{"alias_kind":"pith_short_12","alias_value":"YNXJ6W76QQ43","created_at":"2026-07-05T09:36:56Z"},{"alias_kind":"pith_short_16","alias_value":"YNXJ6W76QQ436QRP","created_at":"2026-07-05T09:36:56Z"},{"alias_kind":"pith_short_8","alias_value":"YNXJ6W76","created_at":"2026-07-05T09:36:56Z"}],"graph_snapshots":[{"event_id":"sha256:36de2cb5f10d71ee1f470e513cecaaebafe0597cd326543792736a47a14d302e","target":"graph","created_at":"2026-07-05T09:36:56Z","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/2411.11457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-Free Reinforcement Learning (RL) algorithms either learn how to map states to expected rewards or search for policies that can maximize a certain performance function. Model-Based algorithms instead, aim to learn an approximation of the underlying model of the RL environment and then use it in combination with planning algorithms. Upside-Down Reinforcement Learning (UDRL) is a novel learning paradigm that aims to learn how to predict actions from states and desired commands. This task is formulated as a Supervised Learning problem and has successfully been tackled by Neural Networks (NNs","authors_text":"Juan Cardenas-Cartagena, Marco Zullich, Massimiliano Falzari, Matthia Sabatelli","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T10:44:20Z","title":"Upside-Down Reinforcement Learning for More Interpretable Optimal Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11457","kind":"arxiv","version":1},"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":"sha256:7840a1ae6b24bb9b0e8e32a28d7e068544914ae34d5835e39856b42e7b7c381c","target":"record","created_at":"2026-07-05T09:36:56Z","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":"8b67c6f968a26ad35ad56eb2d68b956b2d11c49dd64b44c9ad1e658dffde3c81","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T10:44:20Z","title_canon_sha256":"daa9861dfe11420ae30c0fb8d50280f7bf48941aab3f57d5f789769aeadd1362"},"schema_version":"1.0","source":{"id":"2411.11457","kind":"arxiv","version":1}},"canonical_sha256":"c36e9f5bfe8439bf422f89f9fcf5e80c3b6488c9288ebbaf9e3867e6146e4d7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c36e9f5bfe8439bf422f89f9fcf5e80c3b6488c9288ebbaf9e3867e6146e4d7a","first_computed_at":"2026-07-05T09:36:56.656459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:56.656459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gvGyCavOGGXILuVLuI+k36Re9+Lcum0hZRyEYz6fQGehZNBQ/NPzmU/V9ISlNmM2dCn3CdsWf0kOlXmIMaVvCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:56.656916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.11457","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7840a1ae6b24bb9b0e8e32a28d7e068544914ae34d5835e39856b42e7b7c381c","sha256:36de2cb5f10d71ee1f470e513cecaaebafe0597cd326543792736a47a14d302e"],"state_sha256":"a9ba8bc876776c3d385945c084f99ae18be4799e5ab883d795690d0ca8ea9028"}