{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/nethack/papers/ran/1","list_of":"/task/nethack","task":"NetHack","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,14],"of":14,"counts":{"archive_papers_tagged":28,"with_a_code_link":22,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":28,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/nethack/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/online-intrinsic-rewards-for-decision-making","slug":"online-intrinsic-rewards-for-decision-making","title":"Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback","date":"2024-10-30","arxiv_id":"2410.23022","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/online-intrinsic-rewards-for-decision-making#ran","syntology_url":"https://syntology.ai/paper/2410.23022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23022"}},"official":{"repos":["facebookresearch/oni"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/playing-nethack-with-llms-potential","slug":"playing-nethack-with-llms-potential","title":"Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents","date":"2024-03-01","arxiv_id":"2403.00690","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/playing-nethack-with-llms-potential#ran","syntology_url":"https://syntology.ai/paper/2403.00690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00690"}},"official":{"repos":["commandercero/netplay"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/craftax-a-lightning-fast-benchmark-for-open","slug":"craftax-a-lightning-fast-benchmark-for-open","title":"Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning","date":"2024-02-26","arxiv_id":"2402.16801","repositories_listed":1,"syntology":{"n":16,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/craftax-a-lightning-fast-benchmark-for-open#ran","syntology_url":"https://syntology.ai/paper/2402.16801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16801"}},"official":{"repos":["michaeltmatthews/craftax"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/skill-set-optimization-reinforcing-language","slug":"skill-set-optimization-reinforcing-language","title":"Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills","date":"2024-02-05","arxiv_id":"2402.03244","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/skill-set-optimization-reinforcing-language#ran","syntology_url":"https://syntology.ai/paper/2402.03244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03244"}},"official":{"repos":["allenai/sso"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/diff-history-for-long-context-language-agents","slug":"diff-history-for-long-context-language-agents","title":"diff History for Neural Language Agents","date":"2023-12-12","arxiv_id":"2312.07540","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diff-history-for-long-context-language-agents#ran","syntology_url":"https://syntology.ai/paper/2312.07540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07540"}},"official":{"repos":["upiterbarg/diff_history"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/motif-intrinsic-motivation-from-artificial","slug":"motif-intrinsic-motivation-from-artificial","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","date":"2023-09-29","arxiv_id":"2310.00166","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/motif-intrinsic-motivation-from-artificial#ran","syntology_url":"https://syntology.ai/paper/2310.00166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00166"}},"official":{"repos":["facebookresearch/motif"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-laws-for-imitation-learning-in","slug":"scaling-laws-for-imitation-learning-in","title":"Scaling Laws for Imitation Learning in Single-Agent Games","date":"2023-07-18","arxiv_id":"2307.09423","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-laws-for-imitation-learning-in#ran","syntology_url":"https://syntology.ai/paper/2307.09423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09423"}},"official":{"repos":["princeton-nlp/il-scaling-in-games"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/katakomba-tools-and-benchmarks-for-data","slug":"katakomba-tools-and-benchmarks-for-data","title":"Katakomba: Tools and Benchmarks for Data-Driven NetHack","date":"2023-06-14","arxiv_id":"2306.08772","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/katakomba-tools-and-benchmarks-for-data#ran","syntology_url":"https://syntology.ai/paper/2306.08772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08772"}},"official":{"repos":["corl-team/katakomba"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dungeons-and-data-a-large-scale-nethack","slug":"dungeons-and-data-a-large-scale-nethack","title":"Dungeons and Data: A Large-Scale NetHack Dataset","date":"2022-11-01","arxiv_id":"2211.00539","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dungeons-and-data-a-large-scale-nethack#ran","syntology_url":"https://syntology.ai/paper/2211.00539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.00539"}},"official":{"repos":["facebookresearch/nle"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-policy-learning-via-language","slug":"improving-policy-learning-via-language","title":"Improving Policy Learning via Language Dynamics Distillation","date":"2022-09-30","arxiv_id":"2210.00066","repositories_listed":1,"syntology":{"n":8,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/improving-policy-learning-via-language#ran","syntology_url":"https://syntology.ai/paper/2210.00066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.00066"}},"official":{"repos":["vzhong/language-dynamics-distillation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/hierarchical-kickstarting-for-skill-transfer","slug":"hierarchical-kickstarting-for-skill-transfer","title":"Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning","date":"2022-07-23","arxiv_id":"2207.11584","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hierarchical-kickstarting-for-skill-transfer#ran","syntology_url":"https://syntology.ai/paper/2207.11584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.11584"}},"official":{"repos":["ucl-dark/skillhack"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/insights-from-the-neurips-2021-nethack","slug":"insights-from-the-neurips-2021-nethack","title":"Insights From the NeurIPS 2021 NetHack Challenge","date":"2022-03-22","arxiv_id":"2203.11889","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/insights-from-the-neurips-2021-nethack#ran","syntology_url":"https://syntology.ai/paper/2203.11889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11889"}},"official":null}},{"url":"/paper/silg-the-multi-environment-symbolic","slug":"silg-the-multi-environment-symbolic","title":"SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmark","date":"2021-10-20","arxiv_id":"2110.10661","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/silg-the-multi-environment-symbolic#ran","syntology_url":"https://syntology.ai/paper/2110.10661","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.10661"}},"official":{"repos":["vzhong/silg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/the-nethack-learning-environment","slug":"the-nethack-learning-environment","title":"The NetHack Learning Environment","date":"2020-06-24","arxiv_id":"2006.13760","repositories_listed":3,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/the-nethack-learning-environment#ran","syntology_url":"https://syntology.ai/paper/2006.13760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13760"}},"official":{"repos":["facebookresearch/nle"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]}}}],"record_sha256":"f678220dfad8bd07ac2541827472bf316abbcfd7b5630c4f524699b576d9bfb4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}