{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JZFBZH74GSE6SSYIU6LZULQUSC","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":"193e2262951716436dce8f4884352a05296a285a6392d9106b018e38e0a2a975","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-02T07:20:08Z","title_canon_sha256":"d005134e17128808864ea15dbd7c5e7451290624bd12c0fa5f3c6c891f644c3f"},"schema_version":"1.0","source":{"id":"2406.00645","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00645","created_at":"2026-07-05T08:27:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00645v2","created_at":"2026-07-05T08:27:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00645","created_at":"2026-07-05T08:27:26Z"},{"alias_kind":"pith_short_12","alias_value":"JZFBZH74GSE6","created_at":"2026-07-05T08:27:26Z"},{"alias_kind":"pith_short_16","alias_value":"JZFBZH74GSE6SSYI","created_at":"2026-07-05T08:27:26Z"},{"alias_kind":"pith_short_8","alias_value":"JZFBZH74","created_at":"2026-07-05T08:27:26Z"}],"graph_snapshots":[{"event_id":"sha256:8419d0bb5d8e27ceb8963585de1cef255e0bfab63aedddd52092966502337abe","target":"graph","created_at":"2026-07-05T08:27:26Z","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/2406.00645/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we investigate how to leverage pre-trained visual-language models (VLM) for online Reinforcement Learning (RL). In particular, we focus on sparse reward tasks with pre-defined textual task descriptions. We first identify the problem of reward misalignment when applying VLM as a reward in RL tasks. To address this issue, we introduce a lightweight fine-tuning method, named Fuzzy VLM reward-aided RL (FuRL), based on reward alignment and relay RL. Specifically, we enhance the performance of SAC/DrQ baseline agents on sparse reward tasks by fine-tuning VLM representations and using r","authors_text":"Benoit Boulet, Di Wu, Haichao Zhang, Wei Xu, Yuwei Fu","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-02T07:20:08Z","title":"FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00645","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":"sha256:3a0d24907db7dab1c41660372666931481e45e046f691b5365ac096ec995b1fb","target":"record","created_at":"2026-07-05T08:27:26Z","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":"193e2262951716436dce8f4884352a05296a285a6392d9106b018e38e0a2a975","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-02T07:20:08Z","title_canon_sha256":"d005134e17128808864ea15dbd7c5e7451290624bd12c0fa5f3c6c891f644c3f"},"schema_version":"1.0","source":{"id":"2406.00645","kind":"arxiv","version":2}},"canonical_sha256":"4e4a1c9ffc3489e94b08a7979a2e1490abae3af62b6a3edbb9f3fdd1a0224012","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e4a1c9ffc3489e94b08a7979a2e1490abae3af62b6a3edbb9f3fdd1a0224012","first_computed_at":"2026-07-05T08:27:26.521422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:26.521422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+shRwonwjp8mew6rUappqo58QeLOrcEN5BdKGwuC58DTtmB/7E4/j9Qfhih72cHNmJiwVEaOV6s7QllO/aBLAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:26.521839Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00645","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a0d24907db7dab1c41660372666931481e45e046f691b5365ac096ec995b1fb","sha256:8419d0bb5d8e27ceb8963585de1cef255e0bfab63aedddd52092966502337abe"],"state_sha256":"7ef1104217f3d2babc916deb3e43afb2b33c2a0c2bf77053c11a0a3a6544abb8"}