{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/furl-visual-language-models-as-fuzzy-rewards","title":"FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning","arxiv_id":"2406.00645","date":"2024-06-02","proceeding":null,"authors":["Yuwei Fu","Haichao Zhang","Di wu","Wei Xu","Benoit Boulet"],"abstract":"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 relay RL to avoid local minima. Extensive experiments on the Meta-world benchmark tasks demonstrate the efficacy of the proposed method. Code is available at: https://github.com/fuyw/FuRL.","url_abs":"https://arxiv.org/abs/2406.00645v2","url_pdf":"https://arxiv.org/pdf/2406.00645v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"furl-visual-language-models-as-fuzzy-rewards","repo_url":"https://github.com/fuyw/furl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.00645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00645"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/fuyw/FuRL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fuyw/furl","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"c08628fe9b6245db","entry":"crop_center","repo":"fuyw/FuRL","repo_kind":"official","path":"experiments/train_furl.py","file_url":"https://github.com/fuyw/FuRL/blob/HEAD/experiments/train_furl.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c08628fe9b6245db"}},{"code_sha256_prefix":"88369aa7aff57906","entry":"target_update","repo":"fuyw/furl","repo_kind":"official","path":"models/furl.py","file_url":"https://github.com/fuyw/furl/blob/HEAD/models/furl.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"88369aa7aff57906"}},{"code_sha256_prefix":"29a90d6331fc3c39","entry":"FuRLAgent","repo":"fuyw/furl","repo_kind":"official","path":"models/furl.py","file_url":"https://github.com/fuyw/furl/blob/HEAD/models/furl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"29a90d6331fc3c39"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}