{"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/policy-optimization-in-rlhf-the-impact-of-out","title":"Policy Optimization in RLHF: The Impact of Out-of-preference Data","arxiv_id":"2312.10584","date":"2023-12-17","proceeding":null,"authors":["Ziniu Li","Tian Xu","Yang Yu"],"abstract":"Aligning intelligent agents with human preferences and values is important. This paper examines two popular alignment methods: Direct Preference Optimization (DPO) and Reward-Model-Based Policy Optimization (RMB-PO). A variant of RMB-PO, referred to as RMB-PO+ is also considered. These methods, either explicitly or implicitly, learn a reward model from preference data and differ in the data used for policy optimization to unlock the generalization ability of the reward model. In particular, compared with DPO, RMB-PO additionally uses policy-generated data, and RMB-PO+ further leverages new, preference-free data. We examine the impact of such out-of-preference data. Our study, conducted through controlled and synthetic experiments, demonstrates that DPO performs poorly, whereas RMB-PO+ performs the best. In particular, even when providing the policy model with a good feature representation, we find that policy optimization with adequate out-of-preference data significantly improves performance by harnessing the reward model's generalization capabilities.","url_abs":"https://arxiv.org/abs/2312.10584v2","url_pdf":"https://arxiv.org/pdf/2312.10584v2.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":"policy-optimization-in-rlhf-the-impact-of-out","repo_url":"https://github.com/liziniu/policy_optimization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"dpo","method_name":"DPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2312.10584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10584"}},"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/liziniu/policy_optimization","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"c16907ac454ec486","entry":"get_reward_func","repo":"liziniu/policy_optimization","repo_kind":"official","path":"experiments/run_linear_bandit.py","file_url":"https://github.com/liziniu/policy_optimization/blob/HEAD/experiments/run_linear_bandit.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":"c16907ac454ec486"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}