{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EWEVCS3J7EUN77RM2CQUIPL6NL","short_pith_number":"pith:EWEVCS3J","schema_version":"1.0","canonical_sha256":"2589514b69f928dffe2cd0a1443d7e6ae5cf413bafa25cb0342aeebe3e2b007b","source":{"kind":"arxiv","id":"2402.15957","version":2},"attestation_state":"computed","paper":{"title":"DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anthony Liang, Chih-wei Hsu, Craig Boutilier, Erdem B{\\i}y{\\i}k, Guy Tennenholtz, Yinlam Chow","submitted_at":"2024-02-25T02:36:03Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.15957","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-25T02:36:03Z","cross_cats_sorted":[],"title_canon_sha256":"259d0c067823d93a55204575dba7d9b69fe98c564b7184c7a4c16d30d0ea7420","abstract_canon_sha256":"3fc44fab32ec1f7068056bfcadcc4a99eecd96819c530544dee2145872288585"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:07.719101Z","signature_b64":"Z5/qbHMBjBgc8TA+4s3keQETxVmvjC1sdsmx5MN3okfrf+s3vS13rysuErBzTGHbX62dHFkgqtP2bNapBk+uDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2589514b69f928dffe2cd0a1443d7e6ae5cf413bafa25cb0342aeebe3e2b007b","last_reissued_at":"2026-07-05T09:44:07.718615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:07.718615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anthony Liang, Chih-wei Hsu, Craig Boutilier, Erdem B{\\i}y{\\i}k, Guy Tennenholtz, Yinlam Chow","submitted_at":"2024-02-25T02:36:03Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15957","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.15957/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.15957","created_at":"2026-07-05T09:44:07.718675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15957v2","created_at":"2026-07-05T09:44:07.718675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15957","created_at":"2026-07-05T09:44:07.718675+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWEVCS3J7EUN","created_at":"2026-07-05T09:44:07.718675+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWEVCS3J7EUN77RM","created_at":"2026-07-05T09:44:07.718675+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWEVCS3J","created_at":"2026-07-05T09:44:07.718675+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16054","citing_title":"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWEVCS3J7EUN77RM2CQUIPL6NL","json":"https://pith.science/pith/EWEVCS3J7EUN77RM2CQUIPL6NL.json","graph_json":"https://pith.science/api/pith-number/EWEVCS3J7EUN77RM2CQUIPL6NL/graph.json","events_json":"https://pith.science/api/pith-number/EWEVCS3J7EUN77RM2CQUIPL6NL/events.json","paper":"https://pith.science/paper/EWEVCS3J"},"agent_actions":{"view_html":"https://pith.science/pith/EWEVCS3J7EUN77RM2CQUIPL6NL","download_json":"https://pith.science/pith/EWEVCS3J7EUN77RM2CQUIPL6NL.json","view_paper":"https://pith.science/paper/EWEVCS3J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15957&json=true","fetch_graph":"https://pith.science/api/pith-number/EWEVCS3J7EUN77RM2CQUIPL6NL/graph.json","fetch_events":"https://pith.science/api/pith-number/EWEVCS3J7EUN77RM2CQUIPL6NL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWEVCS3J7EUN77RM2CQUIPL6NL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWEVCS3J7EUN77RM2CQUIPL6NL/action/storage_attestation","attest_author":"https://pith.science/pith/EWEVCS3J7EUN77RM2CQUIPL6NL/action/author_attestation","sign_citation":"https://pith.science/pith/EWEVCS3J7EUN77RM2CQUIPL6NL/action/citation_signature","submit_replication":"https://pith.science/pith/EWEVCS3J7EUN77RM2CQUIPL6NL/action/replication_record"}},"created_at":"2026-07-05T09:44:07.718675+00:00","updated_at":"2026-07-05T09:44:07.718675+00:00"}