{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7VN7NXT5Z7DH45VYIAYP6EYLQS","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":"b9091d9fba3798ce570eb7254c9ab5bc2ebb13faba528838a1c72234f90fdec5","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-28T12:05:47Z","title_canon_sha256":"9066639295aaa54aeb76cd880aaf0beba87fb481a11d127dbc4b21103511fd76"},"schema_version":"1.0","source":{"id":"2406.19861","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19861","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19861v2","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19861","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"pith_short_12","alias_value":"7VN7NXT5Z7DH","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"pith_short_16","alias_value":"7VN7NXT5Z7DH45VY","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"pith_short_8","alias_value":"7VN7NXT5","created_at":"2026-07-05T09:28:52Z"}],"graph_snapshots":[{"event_id":"sha256:5fb2e9103291fa450bd82a961cd804936221042cbc223510ee183a9eaec1af7f","target":"graph","created_at":"2026-07-05T09:28:52Z","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/2406.19861/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy Mirror Descent (PMD) is a powerful and theoretically sound methodology for sequential decision-making. However, it is not directly applicable to Reinforcement Learning (RL) due to the inaccessibility of explicit action-value functions. We address this challenge by introducing a novel approach based on learning a world model of the environment using conditional mean embeddings. Leveraging tools from operator theory we derive a closed-form expression of the action-value function in terms of the world model via simple matrix operations. Combining these estimators with PMD leads to POWR, a ","authors_text":"Carlo Ciliberto, Marco Prattic\\`o, Massimiliano Pontil, Pietro Novelli","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-28T12:05:47Z","title":"Operator World Models for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19861","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:de4e4f99ca67cb24798a0353d2371ef7bf9c4bb1386dd15f250d413bab71a9fc","target":"record","created_at":"2026-07-05T09:28:52Z","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":"b9091d9fba3798ce570eb7254c9ab5bc2ebb13faba528838a1c72234f90fdec5","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-28T12:05:47Z","title_canon_sha256":"9066639295aaa54aeb76cd880aaf0beba87fb481a11d127dbc4b21103511fd76"},"schema_version":"1.0","source":{"id":"2406.19861","kind":"arxiv","version":2}},"canonical_sha256":"fd5bf6de7dcfc67e76b84030ff130b8484c48b6433b03c5d7b048b4fd77d7d58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd5bf6de7dcfc67e76b84030ff130b8484c48b6433b03c5d7b048b4fd77d7d58","first_computed_at":"2026-07-05T09:28:52.534167Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:52.534167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Pw+xlImRRmsTcV60U6K6a7jdJDoSQA9cpbkJsF07t/QnHN3Y83/bj/mV3Rj3A8mVvoduznmwYMnTyJz2QkcBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:52.534683Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.19861","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de4e4f99ca67cb24798a0353d2371ef7bf9c4bb1386dd15f250d413bab71a9fc","sha256:5fb2e9103291fa450bd82a961cd804936221042cbc223510ee183a9eaec1af7f"],"state_sha256":"a0fdaf811fc5dcbdbfaa26bf5b1b746f28889d60281104b063557e688ce9cc42"}