{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AVY67346HWLHU7TYFHO4FDDIIJ","short_pith_number":"pith:AVY67346","schema_version":"1.0","canonical_sha256":"0571efef9e3d967a7e7829ddc28c68426042388747669274d90f6bb77e04a15b","source":{"kind":"arxiv","id":"2312.05465","version":1},"attestation_state":"computed","paper":{"title":"On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Giho Kim, Howon Lee, Insoon Yang, Jaeuk Shin, Joonho Han","submitted_at":"2023-12-09T04:52:28Z","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"},"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":"2312.05465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-09T04:52:28Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"9e8f7dc70ae1a05306bcffc995ace64ac6282ef1b4911b8a905988bffa24795c","abstract_canon_sha256":"66f2c4048f0c3a187d57b5949ed241e6b4e89fefc5d6e79106de7d75baced724"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:04.900076Z","signature_b64":"6r8Fy2tJ60Un/1ijuA0a/rubJl6vbri9a8VDrWPCPxwavDViSskdQX5PFPV50LPcLfVTRmxvriDKy5qPioB4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0571efef9e3d967a7e7829ddc28c68426042388747669274d90f6bb77e04a15b","last_reissued_at":"2026-07-05T07:22:04.899606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:04.899606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Giho Kim, Howon Lee, Insoon Yang, Jaeuk Shin, Joonho Han","submitted_at":"2023-12-09T04:52:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05465","kind":"arxiv","version":1},"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/2312.05465/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":"2312.05465","created_at":"2026-07-05T07:22:04.899654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05465v1","created_at":"2026-07-05T07:22:04.899654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05465","created_at":"2026-07-05T07:22:04.899654+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVY67346HWLH","created_at":"2026-07-05T07:22:04.899654+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVY67346HWLHU7TY","created_at":"2026-07-05T07:22:04.899654+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVY67346","created_at":"2026-07-05T07:22:04.899654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02332","citing_title":"Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AVY67346HWLHU7TYFHO4FDDIIJ","json":"https://pith.science/pith/AVY67346HWLHU7TYFHO4FDDIIJ.json","graph_json":"https://pith.science/api/pith-number/AVY67346HWLHU7TYFHO4FDDIIJ/graph.json","events_json":"https://pith.science/api/pith-number/AVY67346HWLHU7TYFHO4FDDIIJ/events.json","paper":"https://pith.science/paper/AVY67346"},"agent_actions":{"view_html":"https://pith.science/pith/AVY67346HWLHU7TYFHO4FDDIIJ","download_json":"https://pith.science/pith/AVY67346HWLHU7TYFHO4FDDIIJ.json","view_paper":"https://pith.science/paper/AVY67346","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05465&json=true","fetch_graph":"https://pith.science/api/pith-number/AVY67346HWLHU7TYFHO4FDDIIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/AVY67346HWLHU7TYFHO4FDDIIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVY67346HWLHU7TYFHO4FDDIIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVY67346HWLHU7TYFHO4FDDIIJ/action/storage_attestation","attest_author":"https://pith.science/pith/AVY67346HWLHU7TYFHO4FDDIIJ/action/author_attestation","sign_citation":"https://pith.science/pith/AVY67346HWLHU7TYFHO4FDDIIJ/action/citation_signature","submit_replication":"https://pith.science/pith/AVY67346HWLHU7TYFHO4FDDIIJ/action/replication_record"}},"created_at":"2026-07-05T07:22:04.899654+00:00","updated_at":"2026-07-05T07:22:04.899654+00:00"}