{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OX4FO4XHRIL2O5HM5LMGJVEKRA","short_pith_number":"pith:OX4FO4XH","schema_version":"1.0","canonical_sha256":"75f85772e78a17a774ecead864d48a883445099e87fe7fddf7d894b2ea0d6d8d","source":{"kind":"arxiv","id":"2502.02834","version":3},"attestation_state":"computed","paper":{"title":"Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jeongmo Kim, Minung Kim, Seungyul Han, Yisak Park","submitted_at":"2025-02-05T02:31:50Z","abstract_excerpt":"Meta reinforcement learning aims to develop policies that generalize to unseen tasks sampled from a task distribution. While context-based meta-RL methods improve task representation using task latents, they often struggle with out-of-distribution (OOD) tasks. To address this, we propose Task-Aware Virtual Training (TAVT), a novel algorithm that accurately captures task characteristics for both training and OOD scenarios using metric-based representation learning. Our method successfully preserves task characteristics in virtual tasks and employs a state regularization technique to mitigate ov"},"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":"2502.02834","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T02:31:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"14c51254420642ef4a9d060ca2f8157fb652abc8f8d8273a07eab355a90c50d7","abstract_canon_sha256":"20c5c8272be66218a3350667ae0afdc15127834650736d1921ad7afc88e96c00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:12.697620Z","signature_b64":"96QIPhjBv00rVVHb7V/YAyWj7b5t57TbrWnP8HCHey9id3FwgrpFt4TYz/ztG9DhLWGj82tBRPyh6Hpjs/vbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75f85772e78a17a774ecead864d48a883445099e87fe7fddf7d894b2ea0d6d8d","last_reissued_at":"2026-05-21T01:04:12.696830Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:12.696830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jeongmo Kim, Minung Kim, Seungyul Han, Yisak Park","submitted_at":"2025-02-05T02:31:50Z","abstract_excerpt":"Meta reinforcement learning aims to develop policies that generalize to unseen tasks sampled from a task distribution. While context-based meta-RL methods improve task representation using task latents, they often struggle with out-of-distribution (OOD) tasks. To address this, we propose Task-Aware Virtual Training (TAVT), a novel algorithm that accurately captures task characteristics for both training and OOD scenarios using metric-based representation learning. Our method successfully preserves task characteristics in virtual tasks and employs a state regularization technique to mitigate ov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02834","kind":"arxiv","version":3},"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/2502.02834/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":"2502.02834","created_at":"2026-05-21T01:04:12.696961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02834v3","created_at":"2026-05-21T01:04:12.696961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02834","created_at":"2026-05-21T01:04:12.696961+00:00"},{"alias_kind":"pith_short_12","alias_value":"OX4FO4XHRIL2","created_at":"2026-05-21T01:04:12.696961+00:00"},{"alias_kind":"pith_short_16","alias_value":"OX4FO4XHRIL2O5HM","created_at":"2026-05-21T01:04:12.696961+00:00"},{"alias_kind":"pith_short_8","alias_value":"OX4FO4XH","created_at":"2026-05-21T01:04:12.696961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.23448","citing_title":"An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OX4FO4XHRIL2O5HM5LMGJVEKRA","json":"https://pith.science/pith/OX4FO4XHRIL2O5HM5LMGJVEKRA.json","graph_json":"https://pith.science/api/pith-number/OX4FO4XHRIL2O5HM5LMGJVEKRA/graph.json","events_json":"https://pith.science/api/pith-number/OX4FO4XHRIL2O5HM5LMGJVEKRA/events.json","paper":"https://pith.science/paper/OX4FO4XH"},"agent_actions":{"view_html":"https://pith.science/pith/OX4FO4XHRIL2O5HM5LMGJVEKRA","download_json":"https://pith.science/pith/OX4FO4XHRIL2O5HM5LMGJVEKRA.json","view_paper":"https://pith.science/paper/OX4FO4XH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02834&json=true","fetch_graph":"https://pith.science/api/pith-number/OX4FO4XHRIL2O5HM5LMGJVEKRA/graph.json","fetch_events":"https://pith.science/api/pith-number/OX4FO4XHRIL2O5HM5LMGJVEKRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OX4FO4XHRIL2O5HM5LMGJVEKRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OX4FO4XHRIL2O5HM5LMGJVEKRA/action/storage_attestation","attest_author":"https://pith.science/pith/OX4FO4XHRIL2O5HM5LMGJVEKRA/action/author_attestation","sign_citation":"https://pith.science/pith/OX4FO4XHRIL2O5HM5LMGJVEKRA/action/citation_signature","submit_replication":"https://pith.science/pith/OX4FO4XHRIL2O5HM5LMGJVEKRA/action/replication_record"}},"created_at":"2026-05-21T01:04:12.696961+00:00","updated_at":"2026-05-21T01:04:12.696961+00:00"}