{"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/revisiting-the-weaknesses-of-reinforcement-1","title":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","arxiv_id":"2106.08942","date":"2021-06-16","proceeding":"NAACL 2021 4","authors":["Samuel Kiegeland","Julia Kreutzer"],"abstract":"Policy gradient algorithms have found wide adoption in NLP, but have recently become subject to criticism, doubting their suitability for NMT. Choshen et al. (2020) identify multiple weaknesses and suspect that their success is determined by the shape of output distributions rather than the reward. In this paper, we revisit these claims and study them under a wider range of configurations. Our experiments on in-domain and cross-domain adaptation reveal the importance of exploration and reward scaling, and provide empirical counter-evidence to these claims.","url_abs":"https://arxiv.org/abs/2106.08942v1","url_pdf":"https://arxiv.org/pdf/2106.08942v1.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":"revisiting-the-weaknesses-of-reinforcement-1","repo_url":"https://github.com/samuki/reinforce-joey","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2106.08942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08942"}},"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/samuki/reinforce-joey","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"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":"e0cdbcc27a1c011a","entry":"build_scheduler","repo":"samuki/reinforce-joey","repo_kind":"official","path":"joeynmt/builders.py","file_url":"https://github.com/samuki/reinforce-joey/blob/HEAD/joeynmt/builders.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e0cdbcc27a1c011a"}},{"code_sha256_prefix":"09740968923608a5","entry":"make_logger","repo":"samuki/reinforce-joey","repo_kind":"official","path":"joeynmt/helpers.py","file_url":"https://github.com/samuki/reinforce-joey/blob/HEAD/joeynmt/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"09740968923608a5"}},{"code_sha256_prefix":"d2439dd3cffbf595","entry":"make_model_dir","repo":"samuki/reinforce-joey","repo_kind":"official","path":"joeynmt/helpers.py","file_url":"https://github.com/samuki/reinforce-joey/blob/HEAD/joeynmt/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d2439dd3cffbf595"}},{"code_sha256_prefix":"6e236cbe252334c8","entry":"make_retro_logger","repo":"samuki/reinforce-joey","repo_kind":"official","path":"joeynmt/helpers.py","file_url":"https://github.com/samuki/reinforce-joey/blob/HEAD/joeynmt/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6e236cbe252334c8"}},{"code_sha256_prefix":"cb329af957271d21","entry":"token_batch_size_fn","repo":"samuki/reinforce-joey","repo_kind":"official","path":"joeynmt/data.py","file_url":"https://github.com/samuki/reinforce-joey/blob/HEAD/joeynmt/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb329af957271d21"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}