{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7G7HACKSE7M2RMHUCIEGR6YPNP","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":"79c1a561607739d4de6812905d6c064258a351b44e06138102f9f764270ca92d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-29T11:59:03Z","title_canon_sha256":"13d0c8426b43d6f4abb7d626cc6288ff591ce04a9e22f029a8fbec3f5e40cd80"},"schema_version":"1.0","source":{"id":"2311.17565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17565","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17565v1","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17565","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"pith_short_12","alias_value":"7G7HACKSE7M2","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"pith_short_16","alias_value":"7G7HACKSE7M2RMHU","created_at":"2026-07-05T07:18:15Z"},{"alias_kind":"pith_short_8","alias_value":"7G7HACKS","created_at":"2026-07-05T07:18:15Z"}],"graph_snapshots":[{"event_id":"sha256:06a90f43ef01f8d7540f5c39203fbd9b6d98a4a9450cc4e2dfa0dbfe689f08d3","target":"graph","created_at":"2026-07-05T07:18:15Z","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/2311.17565/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In goal-conditioned reinforcement learning (GCRL), sparse rewards present significant challenges, often obstructing efficient learning. Although multi-step GCRL can boost this efficiency, it can also lead to off-policy biases in target values. This paper dives deep into these biases, categorizing them into two distinct categories: \"shooting\" and \"shifting\". Recognizing that certain behavior policies can hasten policy refinement, we present solutions designed to capitalize on the positive aspects of these biases while minimizing their drawbacks, enabling the use of larger step sizes to speed up","authors_text":"Ke Chen, Lisheng Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-29T11:59:03Z","title":"Bias Resilient Multi-Step Off-Policy Goal-Conditioned Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17565","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":"sha256:31da7314e650b9a2345f4e0265fe894d35e2207aaf4d2ed4ce027769037d34a0","target":"record","created_at":"2026-07-05T07:18:15Z","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":"79c1a561607739d4de6812905d6c064258a351b44e06138102f9f764270ca92d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-29T11:59:03Z","title_canon_sha256":"13d0c8426b43d6f4abb7d626cc6288ff591ce04a9e22f029a8fbec3f5e40cd80"},"schema_version":"1.0","source":{"id":"2311.17565","kind":"arxiv","version":1}},"canonical_sha256":"f9be70095227d9a8b0f4120868fb0f6bf5c401d2037dc1df4197a0e7603fdf98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9be70095227d9a8b0f4120868fb0f6bf5c401d2037dc1df4197a0e7603fdf98","first_computed_at":"2026-07-05T07:18:15.590300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:15.590300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8PxV5ghaALj0PiEVhzkcGNbWXo8bYlwc0iK2whD6pINd8Njoj5GIuY6tc+HwYsx3P+DigvZg9APb/RwwQP1hBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:15.590786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31da7314e650b9a2345f4e0265fe894d35e2207aaf4d2ed4ce027769037d34a0","sha256:06a90f43ef01f8d7540f5c39203fbd9b6d98a4a9450cc4e2dfa0dbfe689f08d3"],"state_sha256":"d1e90a485c5e651b7d212d14d2a8271d16d89df28b0103fcc39c819203d5e8f5"}