{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GMXDK37AWBZDGRE75TENHB7FAQ","short_pith_number":"pith:GMXDK37A","schema_version":"1.0","canonical_sha256":"332e356fe0b07233449fecc8d387e5042b833753e84c3de51719ddd9b744adae","source":{"kind":"arxiv","id":"2402.06402","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Transformers are Efficient Meta-Reinforcement Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andr\\'e Biedenkapp, Gresa Shala, Josif Grabocka","submitted_at":"2024-02-09T13:40:11Z","abstract_excerpt":"We introduce Hierarchical Transformers for Meta-Reinforcement Learning (HTrMRL), a powerful online meta-reinforcement learning approach. HTrMRL aims to address the challenge of enabling reinforcement learning agents to perform effectively in previously unseen tasks. We demonstrate how past episodes serve as a rich source of information, which our model effectively distills and applies to new contexts. Our learned algorithm is capable of outperforming the previous state-of-the-art and provides more efficient meta-training while significantly improving generalization capabilities. Experimental r"},"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":"2402.06402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-09T13:40:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5d2d1f7907d639651dd29c323e92bc2eb4241d4a07cfb57dc0ed3d9906b16b29","abstract_canon_sha256":"3d047492160e8c8ca797d2680128ce4ef3d2ebc3b44bae13591332213dbd8e41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:23.738164Z","signature_b64":"z4lGiEZYN1Ff/qdelq9T4KzP670ci5vPam3Ik0w0JLglt9QtZK5EbSCh9c/xKaf+7Z0XGOfoklGkDNro4JVwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"332e356fe0b07233449fecc8d387e5042b833753e84c3de51719ddd9b744adae","last_reissued_at":"2026-07-05T07:43:23.737754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:23.737754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Transformers are Efficient Meta-Reinforcement Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andr\\'e Biedenkapp, Gresa Shala, Josif Grabocka","submitted_at":"2024-02-09T13:40:11Z","abstract_excerpt":"We introduce Hierarchical Transformers for Meta-Reinforcement Learning (HTrMRL), a powerful online meta-reinforcement learning approach. HTrMRL aims to address the challenge of enabling reinforcement learning agents to perform effectively in previously unseen tasks. We demonstrate how past episodes serve as a rich source of information, which our model effectively distills and applies to new contexts. Our learned algorithm is capable of outperforming the previous state-of-the-art and provides more efficient meta-training while significantly improving generalization capabilities. Experimental r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06402","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/2402.06402/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":"2402.06402","created_at":"2026-07-05T07:43:23.737813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.06402v1","created_at":"2026-07-05T07:43:23.737813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06402","created_at":"2026-07-05T07:43:23.737813+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMXDK37AWBZD","created_at":"2026-07-05T07:43:23.737813+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMXDK37AWBZDGRE7","created_at":"2026-07-05T07:43:23.737813+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMXDK37A","created_at":"2026-07-05T07:43:23.737813+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.03752","citing_title":"Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19837","citing_title":"Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent","ref_index":144,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GMXDK37AWBZDGRE75TENHB7FAQ","json":"https://pith.science/pith/GMXDK37AWBZDGRE75TENHB7FAQ.json","graph_json":"https://pith.science/api/pith-number/GMXDK37AWBZDGRE75TENHB7FAQ/graph.json","events_json":"https://pith.science/api/pith-number/GMXDK37AWBZDGRE75TENHB7FAQ/events.json","paper":"https://pith.science/paper/GMXDK37A"},"agent_actions":{"view_html":"https://pith.science/pith/GMXDK37AWBZDGRE75TENHB7FAQ","download_json":"https://pith.science/pith/GMXDK37AWBZDGRE75TENHB7FAQ.json","view_paper":"https://pith.science/paper/GMXDK37A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.06402&json=true","fetch_graph":"https://pith.science/api/pith-number/GMXDK37AWBZDGRE75TENHB7FAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/GMXDK37AWBZDGRE75TENHB7FAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMXDK37AWBZDGRE75TENHB7FAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMXDK37AWBZDGRE75TENHB7FAQ/action/storage_attestation","attest_author":"https://pith.science/pith/GMXDK37AWBZDGRE75TENHB7FAQ/action/author_attestation","sign_citation":"https://pith.science/pith/GMXDK37AWBZDGRE75TENHB7FAQ/action/citation_signature","submit_replication":"https://pith.science/pith/GMXDK37AWBZDGRE75TENHB7FAQ/action/replication_record"}},"created_at":"2026-07-05T07:43:23.737813+00:00","updated_at":"2026-07-05T07:43:23.737813+00:00"}