{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AVY67346HWLHU7TYFHO4FDDIIJ","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":"66f2c4048f0c3a187d57b5949ed241e6b4e89fefc5d6e79106de7d75baced724","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-09T04:52:28Z","title_canon_sha256":"9e8f7dc70ae1a05306bcffc995ace64ac6282ef1b4911b8a905988bffa24795c"},"schema_version":"1.0","source":{"id":"2312.05465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.05465","created_at":"2026-07-05T07:22:04Z"},{"alias_kind":"arxiv_version","alias_value":"2312.05465v1","created_at":"2026-07-05T07:22:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05465","created_at":"2026-07-05T07:22:04Z"},{"alias_kind":"pith_short_12","alias_value":"AVY67346HWLH","created_at":"2026-07-05T07:22:04Z"},{"alias_kind":"pith_short_16","alias_value":"AVY67346HWLHU7TY","created_at":"2026-07-05T07:22:04Z"},{"alias_kind":"pith_short_8","alias_value":"AVY67346","created_at":"2026-07-05T07:22:04Z"}],"graph_snapshots":[{"event_id":"sha256:b20a71e33c9b0b3d49c0502939e1eaa40043bcc46462beeb7fe1fd9310956d33","target":"graph","created_at":"2026-07-05T07:22:04Z","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/2312.05465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing a competent meta-reinforcement learning (meta-RL) algorithm in terms of data usage remains a central challenge to be tackled for its successful real-world applications. In this paper, we propose a sample-efficient meta-RL algorithm that learns a model of the system or environment at hand in a task-directed manner. As opposed to the standard model-based approaches to meta-RL, our method exploits the value information in order to rapidly capture the decision-critical part of the environment. The key component of our method is the loss function for learning the task inference module and","authors_text":"Giho Kim, Howon Lee, Insoon Yang, Jaeuk Shin, Joonho Han","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-09T04:52:28Z","title":"On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05465","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":"sha256:446916350c95e1aadc3daebf8c6f9bcb8d165a86ae1145b033bc115bee9bcc4b","target":"record","created_at":"2026-07-05T07:22:04Z","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":"66f2c4048f0c3a187d57b5949ed241e6b4e89fefc5d6e79106de7d75baced724","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-09T04:52:28Z","title_canon_sha256":"9e8f7dc70ae1a05306bcffc995ace64ac6282ef1b4911b8a905988bffa24795c"},"schema_version":"1.0","source":{"id":"2312.05465","kind":"arxiv","version":1}},"canonical_sha256":"0571efef9e3d967a7e7829ddc28c68426042388747669274d90f6bb77e04a15b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0571efef9e3d967a7e7829ddc28c68426042388747669274d90f6bb77e04a15b","first_computed_at":"2026-07-05T07:22:04.899606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:22:04.899606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6r8Fy2tJ60Un/1ijuA0a/rubJl6vbri9a8VDrWPCPxwavDViSskdQX5PFPV50LPcLfVTRmxvriDKy5qPioB4Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:22:04.900076Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.05465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:446916350c95e1aadc3daebf8c6f9bcb8d165a86ae1145b033bc115bee9bcc4b","sha256:b20a71e33c9b0b3d49c0502939e1eaa40043bcc46462beeb7fe1fd9310956d33"],"state_sha256":"4420a987e9a40302c35ca878965ae23eaba65933cf843d3f1bd40dcb816725cc"}