{"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/rime-robust-preference-based-reinforcement","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","arxiv_id":"2402.17257","date":"2024-02-27","proceeding":null,"authors":["Jie Cheng","Gang Xiong","Xingyuan Dai","Qinghai Miao","Yisheng Lv","Fei-Yue Wang"],"abstract":"Preference-based Reinforcement Learning (PbRL) circumvents the need for reward engineering by harnessing human preferences as the reward signal. However, current PbRL methods excessively depend on high-quality feedback from domain experts, which results in a lack of robustness. In this paper, we present RIME, a robust PbRL algorithm for effective reward learning from noisy preferences. Our method utilizes a sample selection-based discriminator to dynamically filter out noise and ensure robust training. To counteract the cumulative error stemming from incorrect selection, we suggest a warm start for the reward model, which additionally bridges the performance gap during the transition from pre-training to online training in PbRL. Our experiments on robotic manipulation and locomotion tasks demonstrate that RIME significantly enhances the robustness of the state-of-the-art PbRL method. Code is available at https://github.com/CJReinforce/RIME_ICML2024.","url_abs":"https://arxiv.org/abs/2402.17257v4","url_pdf":"https://arxiv.org/pdf/2402.17257v4.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":"rime-robust-preference-based-reinforcement","repo_url":"https://github.com/cjreinforce/rime_icml2024","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.17257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17257"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cjreinforce/rime_icml2024","reach":null}],"summary":{"ran_draft_wrong":1,"ran":2,"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"c9f63eda91e537ab","entry":"KCenterGreedy","repo":"cjreinforce/rime_icml2024","repo_kind":"official","path":"reward_model_RIME.py","file_url":"https://github.com/cjreinforce/rime_icml2024/blob/HEAD/reward_model_RIME.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9f63eda91e537ab"}},{"code_sha256_prefix":"60d6d08eefa30cf7","entry":"RunningMeanStd","repo":"cjreinforce/rime_icml2024","repo_kind":"official","path":"reward_model_RIME.py","file_url":"https://github.com/cjreinforce/rime_icml2024/blob/HEAD/reward_model_RIME.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60d6d08eefa30cf7"}},{"code_sha256_prefix":"cb62f08adea6cf9a","entry":"VideoRecorder","repo":"cjreinforce/rime_icml2024","repo_kind":"official","path":"reward_model_RIME.py","file_url":"https://github.com/cjreinforce/rime_icml2024/blob/HEAD/reward_model_RIME.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb62f08adea6cf9a"}},{"code_sha256_prefix":"3f2a932901a2d3a9","entry":"compute_smallest_dist","repo":"cjreinforce/rime_icml2024","repo_kind":"official","path":"reward_model_RIME.py","file_url":"https://github.com/cjreinforce/rime_icml2024/blob/HEAD/reward_model_RIME.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f2a932901a2d3a9"}},{"code_sha256_prefix":"647e0562be392b5c","entry":"RIMERewardModel","repo":"cjreinforce/rime_icml2024","repo_kind":"official","path":"reward_model_RIME.py","file_url":"https://github.com/cjreinforce/rime_icml2024/blob/HEAD/reward_model_RIME.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"647e0562be392b5c"}},{"code_sha256_prefix":"3a1138fef2b4ce3c","entry":"RewardModel","repo":"cjreinforce/rime_icml2024","repo_kind":"official","path":"reward_model_RIME.py","file_url":"https://github.com/cjreinforce/rime_icml2024/blob/HEAD/reward_model_RIME.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a1138fef2b4ce3c"}},{"code_sha256_prefix":"d4ff9f7ce18e3a94","entry":"make_dir","repo":"cjreinforce/rime_icml2024","repo_kind":"official","path":"reward_model_RIME.py","file_url":"https://github.com/cjreinforce/rime_icml2024/blob/HEAD/reward_model_RIME.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d4ff9f7ce18e3a94"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}