{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5P7AECTHH6MB4EYAMMTAYAIHBN","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":"03c66f35e53e61f433db0c252f114da9c5b6194972148e208ca893a901f2bef1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T05:40:16Z","title_canon_sha256":"cc9d842e17703c424133159532ccf981c0fbf65b819f51fc30157f968aa971a0"},"schema_version":"1.0","source":{"id":"2206.03023","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.03023","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"arxiv_version","alias_value":"2206.03023v2","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03023","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"pith_short_12","alias_value":"5P7AECTHH6MB","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"pith_short_16","alias_value":"5P7AECTHH6MB4EYA","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"pith_short_8","alias_value":"5P7AECTH","created_at":"2026-07-05T05:14:57Z"}],"graph_snapshots":[{"event_id":"sha256:3ad74d627706876b8bd2531786df144d807948285f8f259f2e2c736610256503","target":"graph","created_at":"2026-07-05T05:14:57Z","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/2206.03023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline goal-conditioned reinforcement learning (GCRL) promises general-purpose skill learning in the form of reaching diverse goals from purely offline datasets. We propose $\\textbf{Go}$al-conditioned $f$-$\\textbf{A}$dvantage $\\textbf{R}$egression (GoFAR), a novel regression-based offline GCRL algorithm derived from a state-occupancy matching perspective; the key intuition is that the goal-reaching task can be formulated as a state-occupancy matching problem between a dynamics-abiding imitator agent and an expert agent that directly teleports to the goal. In contrast to prior approaches, GoFA","authors_text":"Dinesh Jayaraman, Jason Yan, Osbert Bastani, Yecheng Jason Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T05:40:16Z","title":"How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03023","kind":"arxiv","version":2},"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":"sha256:47fbdd150f3c53bb42d2b668b1548c281a7f381243d5145ff4c8d1af94f0f62f","target":"record","created_at":"2026-07-05T05:14:57Z","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":"03c66f35e53e61f433db0c252f114da9c5b6194972148e208ca893a901f2bef1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-07T05:40:16Z","title_canon_sha256":"cc9d842e17703c424133159532ccf981c0fbf65b819f51fc30157f968aa971a0"},"schema_version":"1.0","source":{"id":"2206.03023","kind":"arxiv","version":2}},"canonical_sha256":"ebfe020a673f981e130063260c01070b6f6091a1828d6f897990b1f69aceae1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebfe020a673f981e130063260c01070b6f6091a1828d6f897990b1f69aceae1e","first_computed_at":"2026-07-05T05:14:57.748172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:14:57.748172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7BYn/Vfw/zIWcZmzwegqlJG1ZvEiX0oOxyy23l7d4kHKUbt8pm58ATV23QcJh+qJHiX7dQKK/ms+VtCiw1z1DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:14:57.748642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.03023","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47fbdd150f3c53bb42d2b668b1548c281a7f381243d5145ff4c8d1af94f0f62f","sha256:3ad74d627706876b8bd2531786df144d807948285f8f259f2e2c736610256503"],"state_sha256":"3ac7f1d42939aee0d7d499be4e98b0a1b1fae516e0bb7c4068b3fb8fa30fd663"}