{"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/improved-off-policy-reinforcement-learning-in","title":"Improved Off-policy Reinforcement Learning in Biological Sequence Design","arxiv_id":"2410.04461","date":"2024-10-06","proceeding":null,"authors":["Hyeonah Kim","Minsu Kim","Taeyoung Yun","Sanghyeok Choi","Emmanuel Bengio","Alex Hernández-García","Jinkyoo Park"],"abstract":"Designing biological sequences with desired properties is challenging due to vast search spaces and limited evaluation budgets. Although reinforcement learning methods use proxy models for rapid reward evaluation, insufficient training data can cause proxy misspecification on out-of-distribution inputs. To address this, we propose a novel off-policy search, $\\delta$-Conservative Search, that enhances robustness by restricting policy exploration to reliable regions. Starting from high-score offline sequences, we inject noise by randomly masking tokens with probability $\\delta$, then denoise them using our policy. We further adapt $\\delta$ based on proxy uncertainty on each data point, aligning the level of conservativeness with model confidence. Experimental results show that our conservative search consistently enhances the off-policy training, outperforming existing machine learning methods in discovering high-score sequences across diverse tasks, including DNA, RNA, protein, and peptide design.","url_abs":"https://arxiv.org/abs/2410.04461v2","url_pdf":"https://arxiv.org/pdf/2410.04461v2.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":"improved-off-policy-reinforcement-learning-in","repo_url":"https://github.com/hyeonahkimm/delta_cs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.04461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04461"}},"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/hyeonahkimm/delta_cs","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":2,"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":1,"samples":[{"code_sha256_prefix":"a0962a1a5631fcc1","entry":"filter_len","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a0962a1a5631fcc1"}},{"code_sha256_prefix":"410b7bf2bbf18d95","entry":"get_current_radius","repo":"hyeonahkimm/delta_cs","repo_kind":"official","path":"BioSeq-GFN-AL/run_tfbind_delta.py","file_url":"https://github.com/hyeonahkimm/delta_cs/blob/HEAD/BioSeq-GFN-AL/run_tfbind_delta.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"410b7bf2bbf18d95"}},{"code_sha256_prefix":"7a638b085246b050","entry":"get_current_radius","repo":"hyeonahkimm/delta_cs","repo_kind":"official","path":"BioSeq-GFN-AL/run_amp_delta.py","file_url":"https://github.com/hyeonahkimm/delta_cs/blob/HEAD/BioSeq-GFN-AL/run_amp_delta.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7a638b085246b050"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}