{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LXBTOO3VJGL3KIQLIO42ISG5LO","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":"46ee033f0b865824cdfe8d8bdf5979e25263e352c712ba4d69456068a5bfd2be","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-17T13:22:40Z","title_canon_sha256":"e7a6077aa2164717a3fcb334d8609d6d387c56fbc81c2263916afad730d95b61"},"schema_version":"1.0","source":{"id":"2302.08865","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.08865","created_at":"2026-07-05T05:42:55Z"},{"alias_kind":"arxiv_version","alias_value":"2302.08865v1","created_at":"2026-07-05T05:42:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08865","created_at":"2026-07-05T05:42:55Z"},{"alias_kind":"pith_short_12","alias_value":"LXBTOO3VJGL3","created_at":"2026-07-05T05:42:55Z"},{"alias_kind":"pith_short_16","alias_value":"LXBTOO3VJGL3KIQL","created_at":"2026-07-05T05:42:55Z"},{"alias_kind":"pith_short_8","alias_value":"LXBTOO3V","created_at":"2026-07-05T05:42:55Z"}],"graph_snapshots":[{"event_id":"sha256:72d09b796531615310bf70548543e3a53801b8301c38f4c2a58ceee47c8ca557","target":"graph","created_at":"2026-07-05T05:42:55Z","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/2302.08865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline goal-conditioned reinforcement learning (GCRL) can be challenging due to overfitting to the given dataset. To generalize agents' skills outside the given dataset, we propose a goal-swapping procedure that generates additional trajectories. To alleviate the problem of noise and extrapolation errors, we present a general offline reinforcement learning method called deterministic Q-advantage policy gradient (DQAPG). In the experiments, DQAPG outperforms state-of-the-art goal-conditioned offline RL methods in a wide range of benchmark tasks, and goal-swapping further improves the test resu","authors_text":"Dingding Cai, Huiling Wang, Joni-Kristen K\\\"am\\\"ar\\\"ainen, Joni Pajarinen, Wenyan Yang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-17T13:22:40Z","title":"Swapped goal-conditioned offline reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08865","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:aa2977877d4dbb89410d3bdf16412841ce65a7a638fa5325b5a4b13ea0ab8957","target":"record","created_at":"2026-07-05T05:42:55Z","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":"46ee033f0b865824cdfe8d8bdf5979e25263e352c712ba4d69456068a5bfd2be","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-17T13:22:40Z","title_canon_sha256":"e7a6077aa2164717a3fcb334d8609d6d387c56fbc81c2263916afad730d95b61"},"schema_version":"1.0","source":{"id":"2302.08865","kind":"arxiv","version":1}},"canonical_sha256":"5dc3373b754997b5220b43b9a448dd5bbb834d4949c92021f2259e796c84d3b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5dc3373b754997b5220b43b9a448dd5bbb834d4949c92021f2259e796c84d3b4","first_computed_at":"2026-07-05T05:42:55.961106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:42:55.961106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Vpw658haGyLAJK0rM9qy4EqDkVHo2mZ3XPRedzkMUynXqyvqxlFiAl22VlN6yDXbWSZOUipFvY3p/1AM1QtAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:42:55.961507Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.08865","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa2977877d4dbb89410d3bdf16412841ce65a7a638fa5325b5a4b13ea0ab8957","sha256:72d09b796531615310bf70548543e3a53801b8301c38f4c2a58ceee47c8ca557"],"state_sha256":"01e2404408f67cf9a0ed4ef066844e1195906dfb67676c3c879f8e0a26954873"}