{"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-improvement-using-language-feedback","title":"Policy Improvement using Language Feedback Models","arxiv_id":"2402.07876","date":"2024-02-12","proceeding":null,"authors":["Victor Zhong","Dipendra Misra","Xingdi Yuan","Marc-Alexandre Côté"],"abstract":"We introduce Language Feedback Models (LFMs) that identify desirable behaviour - actions that help achieve tasks specified in the instruction - for imitation learning in instruction following. To train LFMs, we obtain feedback from Large Language Models (LLMs) on visual trajectories verbalized to language descriptions. First, by using LFMs to identify desirable behaviour to imitate, we improve in task-completion rate over strong behavioural cloning baselines on three distinct language grounding environments (Touchdown, ScienceWorld, and ALFWorld). Second, LFMs outperform using LLMs as experts to directly predict actions, when controlling for the number of LLM output tokens. Third, LFMs generalize to unseen environments, improving task-completion rate by 3.5-12.0% through one round of adaptation. Finally, LFM can be modified to provide human-interpretable feedback without performance loss, allowing human verification of desirable behaviour for imitation learning.","url_abs":"https://arxiv.org/abs/2402.07876v6","url_pdf":"https://arxiv.org/pdf/2402.07876v6.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-improvement-using-language-feedback","repo_url":"https://github.com/vzhong/language_feedback_models","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"behavioural-cloning","task_name":"Behavioural cloning"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"instruction-following","task_name":"Instruction Following"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.07876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07876"}},"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/vzhong/language_feedback_models","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":"d75641c0350a54f1","entry":"adjust_render","repo":"vzhong/language_feedback_models","repo_kind":"official","path":"experiments/get_llm_feedback.py","file_url":"https://github.com/vzhong/language_feedback_models/blob/HEAD/experiments/get_llm_feedback.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":"d75641c0350a54f1"}},{"code_sha256_prefix":"89b4a69cba8ab5cc","entry":"build_example","repo":"vzhong/language_feedback_models","repo_kind":"official","path":"experiments/build_bc_data.py","file_url":"https://github.com/vzhong/language_feedback_models/blob/HEAD/experiments/build_bc_data.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":"89b4a69cba8ab5cc"}},{"code_sha256_prefix":"fe361276102577d5","entry":"get_prompt","repo":"vzhong/language_feedback_models","repo_kind":"official","path":"experiments/prompt_utils.py","file_url":"https://github.com/vzhong/language_feedback_models/blob/HEAD/experiments/prompt_utils.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":"fe361276102577d5"}},{"code_sha256_prefix":"99f9e3f30575cb13","entry":"query_openai","repo":"vzhong/language_feedback_models","repo_kind":"official","path":"experiments/get_llm_feedback.py","file_url":"https://github.com/vzhong/language_feedback_models/blob/HEAD/experiments/get_llm_feedback.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":"99f9e3f30575cb13"}},{"code_sha256_prefix":"aac32e1aa10ecf97","entry":"setup_openai","repo":"vzhong/language_feedback_models","repo_kind":"official","path":"experiments/get_llm_feedback.py","file_url":"https://github.com/vzhong/language_feedback_models/blob/HEAD/experiments/get_llm_feedback.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":"aac32e1aa10ecf97"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}