{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EWEVCS3J7EUN77RM2CQUIPL6NL","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":"3fc44fab32ec1f7068056bfcadcc4a99eecd96819c530544dee2145872288585","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-25T02:36:03Z","title_canon_sha256":"259d0c067823d93a55204575dba7d9b69fe98c564b7184c7a4c16d30d0ea7420"},"schema_version":"1.0","source":{"id":"2402.15957","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15957","created_at":"2026-07-05T09:44:07Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15957v2","created_at":"2026-07-05T09:44:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15957","created_at":"2026-07-05T09:44:07Z"},{"alias_kind":"pith_short_12","alias_value":"EWEVCS3J7EUN","created_at":"2026-07-05T09:44:07Z"},{"alias_kind":"pith_short_16","alias_value":"EWEVCS3J7EUN77RM","created_at":"2026-07-05T09:44:07Z"},{"alias_kind":"pith_short_8","alias_value":"EWEVCS3J","created_at":"2026-07-05T09:44:07Z"}],"graph_snapshots":[{"event_id":"sha256:9758b77ab36e2cf6a8737306763847e48004b9cc6393347cbf47bb089f3be494","target":"graph","created_at":"2026-07-05T09:44:07Z","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/2402.15957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce DynaMITE-RL, a meta-reinforcement learning (meta-RL) approach to approximate inference in environments where the latent state evolves at varying rates. We model episode sessions - parts of the episode where the latent state is fixed - and propose three key modifications to existing meta-RL methods: consistency of latent information within sessions, session masking, and prior latent conditioning. We demonstrate the importance of these modifications in various domains, ranging from discrete Gridworld environments to continuous-control and simulated robot assistive tasks, demonstrati","authors_text":"Anthony Liang, Chih-wei Hsu, Craig Boutilier, Erdem B{\\i}y{\\i}k, Guy Tennenholtz, Yinlam Chow","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-25T02:36:03Z","title":"DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15957","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":"sha256:6a7c0598269302899137f4a09789186023e4115434866652cf4b2a672859a2ee","target":"record","created_at":"2026-07-05T09:44:07Z","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":"3fc44fab32ec1f7068056bfcadcc4a99eecd96819c530544dee2145872288585","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-25T02:36:03Z","title_canon_sha256":"259d0c067823d93a55204575dba7d9b69fe98c564b7184c7a4c16d30d0ea7420"},"schema_version":"1.0","source":{"id":"2402.15957","kind":"arxiv","version":2}},"canonical_sha256":"2589514b69f928dffe2cd0a1443d7e6ae5cf413bafa25cb0342aeebe3e2b007b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2589514b69f928dffe2cd0a1443d7e6ae5cf413bafa25cb0342aeebe3e2b007b","first_computed_at":"2026-07-05T09:44:07.718615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:07.718615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z5/qbHMBjBgc8TA+4s3keQETxVmvjC1sdsmx5MN3okfrf+s3vS13rysuErBzTGHbX62dHFkgqtP2bNapBk+uDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:07.719101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15957","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a7c0598269302899137f4a09789186023e4115434866652cf4b2a672859a2ee","sha256:9758b77ab36e2cf6a8737306763847e48004b9cc6393347cbf47bb089f3be494"],"state_sha256":"43c0d6c5899d96cd820cbe9262145e6d4ce0aa0096bbf7c1f4f11ff11d423d44"}