{"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/ask-your-humans-using-human-instructions-to-1","title":"Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning","arxiv_id":"2011.00517","date":"2020-11-01","proceeding":"ICLR 2021 1","authors":["Valerie Chen","Abhinav Gupta","Kenneth Marino"],"abstract":"Complex, multi-task problems have proven to be difficult to solve efficiently in a sparse-reward reinforcement learning setting. In order to be sample efficient, multi-task learning requires reuse and sharing of low-level policies. To facilitate the automatic decomposition of hierarchical tasks, we propose the use of step-by-step human demonstrations in the form of natural language instructions and action trajectories. We introduce a dataset of such demonstrations in a crafting-based grid world. Our model consists of a high-level language generator and low-level policy, conditioned on language. We find that human demonstrations help solve the most complex tasks. We also find that incorporating natural language allows the model to generalize to unseen tasks in a zero-shot setting and to learn quickly from a few demonstrations. Generalization is not only reflected in the actions of the agent, but also in the generated natural language instructions in unseen tasks. Our approach also gives our trained agent interpretable behaviors because it is able to generate a sequence of high-level descriptions of its actions.","url_abs":"https://arxiv.org/abs/2011.00517v3","url_pdf":"https://arxiv.org/pdf/2011.00517v3.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":"ask-your-humans-using-human-instructions-to-1","repo_url":"https://github.com/valeriechen/ask-your-humans","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task 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=2011.00517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.00517"}},"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/valeriechen/ask-your-humans","reach":null}],"summary":{"ran":4,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":7,"samples":[{"code_sha256_prefix":"238dbd9a9658f5cb","entry":"BatchLinear","repo":"valeriechen/ask-your-humans","repo_kind":"official","path":"mazebase-training/pytorchppo/a2c_ppo_acktr/model.py","file_url":"https://github.com/valeriechen/ask-your-humans/blob/HEAD/mazebase-training/pytorchppo/a2c_ppo_acktr/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"238dbd9a9658f5cb"}},{"code_sha256_prefix":"aca79d263c84722a","entry":"BatchMLP","repo":"valeriechen/ask-your-humans","repo_kind":"official","path":"mazebase-training/pytorchppo/a2c_ppo_acktr/model.py","file_url":"https://github.com/valeriechen/ask-your-humans/blob/HEAD/mazebase-training/pytorchppo/a2c_ppo_acktr/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aca79d263c84722a"}},{"code_sha256_prefix":"09c15cf784e2f204","entry":"MazeBaseNetLang","repo":"valeriechen/ask-your-humans","repo_kind":"official","path":"mazebase-training/pytorchppo/a2c_ppo_acktr/model.py","file_url":"https://github.com/valeriechen/ask-your-humans/blob/HEAD/mazebase-training/pytorchppo/a2c_ppo_acktr/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"09c15cf784e2f204"}},{"code_sha256_prefix":"f05d0027f542be9a","entry":"SwitchModule","repo":"valeriechen/ask-your-humans","repo_kind":"official","path":"mazebase-training/pytorchppo/a2c_ppo_acktr/model.py","file_url":"https://github.com/valeriechen/ask-your-humans/blob/HEAD/mazebase-training/pytorchppo/a2c_ppo_acktr/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f05d0027f542be9a"}},{"code_sha256_prefix":"2aa53e7930c2c123","entry":"collate_fn","repo":"valeriechen/ask-your-humans","repo_kind":"official","path":"mazebase-training/train_hierarchy.py","file_url":"https://github.com/valeriechen/ask-your-humans/blob/HEAD/mazebase-training/train_hierarchy.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2aa53e7930c2c123"}},{"code_sha256_prefix":"0f243822437c35b0","entry":"query_db","repo":"valeriechen/ask-your-humans","repo_kind":"official","path":"mazebase-datacollection/app_nodb.py","file_url":"https://github.com/valeriechen/ask-your-humans/blob/HEAD/mazebase-datacollection/app_nodb.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0f243822437c35b0"}},{"code_sha256_prefix":"6aca9ce668926435","entry":"ListModule","repo":"valeriechen/ask-your-humans","repo_kind":"official","path":"mazebase-training/pytorchppo/a2c_ppo_acktr/model.py","file_url":"https://github.com/valeriechen/ask-your-humans/blob/HEAD/mazebase-training/pytorchppo/a2c_ppo_acktr/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6aca9ce668926435"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}