{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OX4FO4XHRIL2O5HM5LMGJVEKRA","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":"20c5c8272be66218a3350667ae0afdc15127834650736d1921ad7afc88e96c00","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T02:31:50Z","title_canon_sha256":"14c51254420642ef4a9d060ca2f8157fb652abc8f8d8273a07eab355a90c50d7"},"schema_version":"1.0","source":{"id":"2502.02834","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02834","created_at":"2026-05-21T01:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02834v3","created_at":"2026-05-21T01:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02834","created_at":"2026-05-21T01:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"OX4FO4XHRIL2","created_at":"2026-05-21T01:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"OX4FO4XHRIL2O5HM","created_at":"2026-05-21T01:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"OX4FO4XH","created_at":"2026-05-21T01:04:12Z"}],"graph_snapshots":[{"event_id":"sha256:bc640a167e124f91a38b57e6f451906f00c9bebdf03d5aa24da940b4689c0581","target":"graph","created_at":"2026-05-21T01:04:12Z","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/2502.02834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jeongmo Kim, Minung Kim, Seungyul Han, Yisak Park","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T02:31:50Z","title":"Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02834","kind":"arxiv","version":3},"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:facb7dd5e38e5a1ca8f57e43478105e5abcafeaaf12a006990faf211213666c5","target":"record","created_at":"2026-05-21T01:04:12Z","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":"20c5c8272be66218a3350667ae0afdc15127834650736d1921ad7afc88e96c00","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T02:31:50Z","title_canon_sha256":"14c51254420642ef4a9d060ca2f8157fb652abc8f8d8273a07eab355a90c50d7"},"schema_version":"1.0","source":{"id":"2502.02834","kind":"arxiv","version":3}},"canonical_sha256":"75f85772e78a17a774ecead864d48a883445099e87fe7fddf7d894b2ea0d6d8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75f85772e78a17a774ecead864d48a883445099e87fe7fddf7d894b2ea0d6d8d","first_computed_at":"2026-05-21T01:04:12.696830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:12.696830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"96QIPhjBv00rVVHb7V/YAyWj7b5t57TbrWnP8HCHey9id3FwgrpFt4TYz/ztG9DhLWGj82tBRPyh6Hpjs/vbAg==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:12.697620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02834","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:facb7dd5e38e5a1ca8f57e43478105e5abcafeaaf12a006990faf211213666c5","sha256:bc640a167e124f91a38b57e6f451906f00c9bebdf03d5aa24da940b4689c0581"],"state_sha256":"7a8d92cc54b6546465ba6ac5d6556e8c5896b425deaebdf52a79c8a2f5362556"}