{"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/curriculum-design-for-teaching-via","title":"Curriculum Design for Teaching via Demonstrations: Theory and Applications","arxiv_id":"2106.04696","date":"2021-06-08","proceeding":"NeurIPS 2021 12","authors":["Gaurav Yengera","Rati Devidze","Parameswaran Kamalaruban","Adish Singla"],"abstract":"We consider the problem of teaching via demonstrations in sequential decision-making settings. In particular, we study how to design a personalized curriculum over demonstrations to speed up the learner's convergence. We provide a unified curriculum strategy for two popular learner models: Maximum Causal Entropy Inverse Reinforcement Learning (MaxEnt-IRL) and Cross-Entropy Behavioral Cloning (CrossEnt-BC). Our unified strategy induces a ranking over demonstrations based on a notion of difficulty scores computed w.r.t. the teacher's optimal policy and the learner's current policy. Compared to the state of the art, our strategy doesn't require access to the learner's internal dynamics and still enjoys similar convergence guarantees under mild technical conditions. Furthermore, we adapt our curriculum strategy to the setting where no teacher agent is present using task-specific difficulty scores. Experiments on a synthetic car driving environment and navigation-based environments demonstrate the effectiveness of our curriculum strategy.","url_abs":"https://arxiv.org/abs/2106.04696v3","url_pdf":"https://arxiv.org/pdf/2106.04696v3.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":"curriculum-design-for-teaching-via","repo_url":"https://github.com/adishs/neurips2021_curriculum-teaching-demonstrations_code","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"sequential-decision-making","task_name":"Sequential Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.04696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04696"}},"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/adishs/neurips2021_curriculum-teaching-demonstrations_code","reach":null}],"summary":{"ran_draft_wrong":6,"ran_honours":1,"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":9,"samples":[{"code_sha256_prefix":"b2fc64a58ea989cd","entry":"compute_exp_rho_bellman","repo":"adishs/neurips2021_curriculum-teaching-demonstrations_code","repo_kind":"official","path":"code_cardriving/IRL/teacher.py","file_url":"https://github.com/adishs/neurips2021_curriculum-teaching-demonstrations_code/blob/HEAD/code_cardriving/IRL/teacher.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b2fc64a58ea989cd"}},{"code_sha256_prefix":"d28c160f2fa1753c","entry":"compute_exp_rho_sampling","repo":"adishs/neurips2021_curriculum-teaching-demonstrations_code","repo_kind":"official","path":"code_cardriving/IRL/teacher.py","file_url":"https://github.com/adishs/neurips2021_curriculum-teaching-demonstrations_code/blob/HEAD/code_cardriving/IRL/teacher.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d28c160f2fa1753c"}},{"code_sha256_prefix":"3e86fc3e0cbb1fa4","entry":"compute_value_bellman","repo":"adishs/neurips2021_curriculum-teaching-demonstrations_code","repo_kind":"official","path":"code_cardriving/IRL/teacher.py","file_url":"https://github.com/adishs/neurips2021_curriculum-teaching-demonstrations_code/blob/HEAD/code_cardriving/IRL/teacher.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3e86fc3e0cbb1fa4"}},{"code_sha256_prefix":"26f74904b2ef3bc0","entry":"generate_episode","repo":"adishs/neurips2021_curriculum-teaching-demonstrations_code","repo_kind":"official","path":"code_cardriving/IRL/teacher.py","file_url":"https://github.com/adishs/neurips2021_curriculum-teaching-demonstrations_code/blob/HEAD/code_cardriving/IRL/teacher.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"26f74904b2ef3bc0"}},{"code_sha256_prefix":"113ce2c0734fb450","entry":"softmax","repo":"adishs/neurips2021_curriculum-teaching-demonstrations_code","repo_kind":"official","path":"code_cardriving/IRL/teacher.py","file_url":"https://github.com/adishs/neurips2021_curriculum-teaching-demonstrations_code/blob/HEAD/code_cardriving/IRL/teacher.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"113ce2c0734fb450"}},{"code_sha256_prefix":"48bdc349ecfacbe6","entry":"solver","repo":"adishs/neurips2021_curriculum-teaching-demonstrations_code","repo_kind":"official","path":"code_cardriving/IRL/teacher.py","file_url":"https://github.com/adishs/neurips2021_curriculum-teaching-demonstrations_code/blob/HEAD/code_cardriving/IRL/teacher.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":"48bdc349ecfacbe6"}},{"code_sha256_prefix":"fd4cee10d947a7f2","entry":"value_iteration","repo":"adishs/neurips2021_curriculum-teaching-demonstrations_code","repo_kind":"official","path":"code_cardriving/IRL/teacher.py","file_url":"https://github.com/adishs/neurips2021_curriculum-teaching-demonstrations_code/blob/HEAD/code_cardriving/IRL/teacher.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fd4cee10d947a7f2"}},{"code_sha256_prefix":"a3809d35ae22432c","entry":"value_iteration_soft","repo":"adishs/neurips2021_curriculum-teaching-demonstrations_code","repo_kind":"official","path":"code_cardriving/IRL/teacher.py","file_url":"https://github.com/adishs/neurips2021_curriculum-teaching-demonstrations_code/blob/HEAD/code_cardriving/IRL/teacher.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a3809d35ae22432c"}},{"code_sha256_prefix":"21e86b1fb6ec104c","entry":"Teacher","repo":"adishs/neurips2021_curriculum-teaching-demonstrations_code","repo_kind":"official","path":"code_cardriving/IRL/teacher.py","file_url":"https://github.com/adishs/neurips2021_curriculum-teaching-demonstrations_code/blob/HEAD/code_cardriving/IRL/teacher.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":"21e86b1fb6ec104c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}