{"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/off-policy-evaluation/papers/ran/1","list_of":"/task/off-policy-evaluation","task":"Off-policy evaluation","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":[1,40],"of":40,"counts":{"archive_papers_tagged":265,"with_a_code_link":102,"where_syntology_ran_a_sample":40,"not_listed_spam_title":0,"listed":265,"listed_where_code_ran":40,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":30,"every_run_a_failure_of_syntologys_instrument":10,"listed_with_a_run_with_no_instrument_failure":30,"listed_every_run_a_failure_of_syntologys_instrument":10,"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/off-policy-evaluation/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/two-way-deconfounder-for-off-policy","slug":"two-way-deconfounder-for-off-policy","title":"Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning","date":"2024-12-08","arxiv_id":"2412.05783","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/two-way-deconfounder-for-off-policy#ran","syntology_url":"https://syntology.ai/paper/2412.05783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05783"}},"official":{"repos":["fsmiu/Two-way-Deconfounder"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/abstract-reward-processes-leveraging-state","slug":"abstract-reward-processes-leveraging-state","title":"Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation","date":"2024-10-03","arxiv_id":"2410.02172","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/abstract-reward-processes-leveraging-state#ran","syntology_url":"https://syntology.ai/paper/2410.02172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02172"}},"official":{"repos":["shreyasc-13/star"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/kernel-metric-learning-for-in-sample-off","slug":"kernel-metric-learning-for-in-sample-off","title":"Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies","date":"2024-05-29","arxiv_id":"2405.18792","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":2,"n_ran_checked":2,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/kernel-metric-learning-for-in-sample-off#ran","syntology_url":"https://syntology.ai/paper/2405.18792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18792"}},"official":{"repos":["haanvid/kmifqe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/logarithmic-smoothing-for-pessimistic-off","slug":"logarithmic-smoothing-for-pessimistic-off","title":"Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning","date":"2024-05-23","arxiv_id":"2405.14335","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/logarithmic-smoothing-for-pessimistic-off#ran","syntology_url":"https://syntology.ai/paper/2405.14335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14335"}},"official":{"repos":["otmhi/offpolicy_ls"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hyperparameter-optimization-can-even-be","slug":"hyperparameter-optimization-can-even-be","title":"Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It","date":"2024-04-23","arxiv_id":"2404.15084","repositories_listed":0,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/hyperparameter-optimization-can-even-be#ran","syntology_url":"https://syntology.ai/paper/2404.15084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15084"}},"official":null}},{"url":"/paper/predictive-performance-comparison-of-decision","slug":"predictive-performance-comparison-of-decision","title":"Predictive Performance Comparison of Decision Policies Under Confounding","date":"2024-04-01","arxiv_id":"2404.00848","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/predictive-performance-comparison-of-decision#ran","syntology_url":"https://syntology.ai/paper/2404.00848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00848"}},"official":{"repos":["lguerdan/icml24_predictive_performance_comparison_dps"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/marginal-density-ratio-for-off-policy-1","slug":"marginal-density-ratio-for-off-policy-1","title":"Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits","date":"2023-12-03","arxiv_id":"2312.01457","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":2,"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/marginal-density-ratio-for-off-policy-1#ran","syntology_url":"https://syntology.ai/paper/2312.01457","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01457"}},"official":{"repos":["faaizt/mr-ope"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/when-is-off-policy-evaluation-useful-a-data","slug":"when-is-off-policy-evaluation-useful-a-data","title":"When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric Perspective","date":"2023-11-23","arxiv_id":"2311.14110","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"5 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/when-is-off-policy-evaluation-useful-a-data#ran","syntology_url":"https://syntology.ai/paper/2311.14110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.14110"}},"official":{"repos":["holarissun/Data-Centric-OPE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-offline-policy-evaluation-and","slug":"robust-offline-policy-evaluation-and","title":"Robust Offline Reinforcement learning with Heavy-Tailed Rewards","date":"2023-10-28","arxiv_id":"2310.18715","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-offline-policy-evaluation-and#ran","syntology_url":"https://syntology.ai/paper/2310.18715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18715"}},"official":{"repos":["mamba413/room"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/state-action-similarity-based-representations-1","slug":"state-action-similarity-based-representations-1","title":"State-Action Similarity-Based Representations for Off-Policy Evaluation","date":"2023-10-27","arxiv_id":"2310.18409","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":3,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":9,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/state-action-similarity-based-representations-1#ran","syntology_url":"https://syntology.ai/paper/2310.18409","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18409"}},"official":{"repos":["badger-rl/rope"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/counterfactual-augmented-importance-sampling-1","slug":"counterfactual-augmented-importance-sampling-1","title":"Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation","date":"2023-10-26","arxiv_id":"2310.17146","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/counterfactual-augmented-importance-sampling-1#ran","syntology_url":"https://syntology.ai/paper/2310.17146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17146"}},"official":{"repos":["mld3/counterfactualannot-semiope"],"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"]}}},{"url":"/paper/learning-action-embeddings-for-off-policy","slug":"learning-action-embeddings-for-off-policy","title":"Learning Action Embeddings for Off-Policy Evaluation","date":"2023-05-06","arxiv_id":"2305.03954","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/learning-action-embeddings-for-off-policy#ran","syntology_url":"https://syntology.ai/paper/2305.03954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.03954"}},"official":{"repos":["amazon-science/ope-learn-action-embeddings"],"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/off-policy-evaluation-for-action-dependent","slug":"off-policy-evaluation-for-action-dependent","title":"Off-Policy Evaluation for Action-Dependent Non-Stationary Environments","date":"2023-01-24","arxiv_id":"2301.10330","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/off-policy-evaluation-for-action-dependent#ran","syntology_url":"https://syntology.ai/paper/2301.10330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.10330"}},"official":{"repos":["yashchandak/activens"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/low-variance-off-policy-evaluation-with-state","slug":"low-variance-off-policy-evaluation-with-state","title":"Low Variance Off-policy Evaluation with State-based Importance Sampling","date":"2022-12-07","arxiv_id":"2212.03932","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/low-variance-off-policy-evaluation-with-state#ran","syntology_url":"https://syntology.ai/paper/2212.03932","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03932"}},"official":{"repos":["bossdm/importancesampling"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/local-metric-learning-for-off-policy","slug":"local-metric-learning-for-off-policy","title":"Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions","date":"2022-10-24","arxiv_id":"2210.13373","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"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) · 5 unverified","sample_list":"/paper/local-metric-learning-for-off-policy#ran","syntology_url":"https://syntology.ai/paper/2210.13373","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13373"}},"official":{"repos":["haanvid/kmis"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/a-policy-guided-imitation-approach-for","slug":"a-policy-guided-imitation-approach-for","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","date":"2022-10-15","arxiv_id":"2210.08323","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/a-policy-guided-imitation-approach-for#ran","syntology_url":"https://syntology.ai/paper/2210.08323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08323"}},"official":{"repos":["ryanxhr/por"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/future-dependent-value-based-off-policy-1","slug":"future-dependent-value-based-off-policy-1","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","date":"2022-07-26","arxiv_id":"2207.13081","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/future-dependent-value-based-off-policy-1#ran","syntology_url":"https://syntology.ai/paper/2207.13081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.13081"}},"official":{"repos":["aiueola/neurips2023-future-dependent-ope"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/coptidice-offline-constrained-reinforcement-1","slug":"coptidice-offline-constrained-reinforcement-1","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","date":"2022-04-19","arxiv_id":"2204.08957","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/coptidice-offline-constrained-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2204.08957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08957"}},"official":{"repos":["deepmind/constrained_optidice"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/model-free-and-model-based-policy-evaluation","slug":"model-free-and-model-based-policy-evaluation","title":"Model-Free and Model-Based Policy Evaluation when Causality is Uncertain","date":"2022-04-02","arxiv_id":"2204.00956","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 2 unverified","sample_list":"/paper/model-free-and-model-based-policy-evaluation#ran","syntology_url":"https://syntology.ai/paper/2204.00956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.00956"}},"official":null}},{"url":"/paper/doubly-robust-distributionally-robust-off","slug":"doubly-robust-distributionally-robust-off","title":"Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning","date":"2022-02-19","arxiv_id":"2202.09667","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/doubly-robust-distributionally-robust-off#ran","syntology_url":"https://syntology.ai/paper/2202.09667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.09667"}},"official":{"repos":["causalml/doubly-robust-dropel"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/off-policy-evaluation-for-large-action-spaces","slug":"off-policy-evaluation-for-large-action-spaces","title":"Off-Policy Evaluation for Large Action Spaces via Embeddings","date":"2022-02-13","arxiv_id":"2202.06317","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/off-policy-evaluation-for-large-action-spaces#ran","syntology_url":"https://syntology.ai/paper/2202.06317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.06317"}},"official":{"repos":["st-tech/zr-obp","usaito/icml2022-mips"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/sope-spectrum-of-off-policy-estimators","slug":"sope-spectrum-of-off-policy-estimators","title":"SOPE: Spectrum of Off-Policy Estimators","date":"2021-11-06","arxiv_id":"2111.03936","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/sope-spectrum-of-off-policy-estimators#ran","syntology_url":"https://syntology.ai/paper/2111.03936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03936"}},"official":{"repos":["pearl-utexas/sope"],"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"]}}},{"url":"/paper/proximal-reinforcement-learning-efficient-off","slug":"proximal-reinforcement-learning-efficient-off","title":"Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes","date":"2021-10-28","arxiv_id":"2110.15332","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/proximal-reinforcement-learning-efficient-off#ran","syntology_url":"https://syntology.ai/paper/2110.15332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15332"}},"official":{"repos":["causalml/proximalrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/state-relevance-for-off-policy-evaluation","slug":"state-relevance-for-off-policy-evaluation","title":"State Relevance for Off-Policy Evaluation","date":"2021-09-13","arxiv_id":"2109.06310","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/state-relevance-for-off-policy-evaluation#ran","syntology_url":"https://syntology.ai/paper/2109.06310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06310"}},"official":{"repos":["dtak/osiris"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-the-robustness-of-off-policy","slug":"evaluating-the-robustness-of-off-policy","title":"Evaluating the Robustness of Off-Policy Evaluation","date":"2021-08-31","arxiv_id":"2108.13703","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/evaluating-the-robustness-of-off-policy#ran","syntology_url":"https://syntology.ai/paper/2108.13703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.13703"}},"official":{"repos":["st-tech/zr-obp","sony/pyieoe"],"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/supervised-off-policy-ranking","slug":"supervised-off-policy-ranking","title":"Supervised Off-Policy Ranking","date":"2021-07-03","arxiv_id":"2107.01360","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/supervised-off-policy-ranking#ran","syntology_url":"https://syntology.ai/paper/2107.01360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.01360"}},"official":{"repos":["SOPR-T/SOPR-T"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unifying-gradient-estimators-for-meta","slug":"unifying-gradient-estimators-for-meta","title":"Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation","date":"2021-06-24","arxiv_id":"2106.13125","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":3,"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/unifying-gradient-estimators-for-meta#ran","syntology_url":"https://syntology.ai/paper/2106.13125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13125"}},"official":{"repos":["robintyh1/neurips2021-meta-gradient-offpolicy-evaluation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/active-offline-policy-selection","slug":"active-offline-policy-selection","title":"Active Offline Policy Selection","date":"2021-06-18","arxiv_id":"2106.10251","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/active-offline-policy-selection#ran","syntology_url":"https://syntology.ai/paper/2106.10251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10251"}},"official":{"repos":["deepmind/active_ops"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-deep-reinforcement-learning-approach-to-4","slug":"a-deep-reinforcement-learning-approach-to-4","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","date":"2021-06-12","arxiv_id":"2106.06854","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/a-deep-reinforcement-learning-approach-to-4#ran","syntology_url":"https://syntology.ai/paper/2106.06854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06854"}},"official":{"repos":["sfujim/SR-DICE"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/off-policy-evaluation-via-adaptive-weighting","slug":"off-policy-evaluation-via-adaptive-weighting","title":"Off-Policy Evaluation via Adaptive Weighting with Data from Contextual Bandits","date":"2021-06-03","arxiv_id":"2106.02029","repositories_listed":1,"syntology":{"n":25,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":12,"n_honours":0,"n_violates":1,"n_no_contract":12,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/off-policy-evaluation-via-adaptive-weighting#ran","syntology_url":"https://syntology.ai/paper/2106.02029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02029"}},"official":{"repos":["gsbDBI/contextual_bandits_evaluation"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":12,"ran_from_kinds":["official"]}}},{"url":"/paper/deeply-debiased-off-policy-interval","slug":"deeply-debiased-off-policy-interval","title":"Deeply-Debiased Off-Policy Interval Estimation","date":"2021-05-10","arxiv_id":"2105.04646","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/deeply-debiased-off-policy-interval#ran","syntology_url":"https://syntology.ai/paper/2105.04646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.04646"}},"official":{"repos":["RunzheStat/D2OPE"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/universal-off-policy-evaluation","slug":"universal-off-policy-evaluation","title":"Universal Off-Policy Evaluation","date":"2021-04-26","arxiv_id":"2104.12820","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/universal-off-policy-evaluation#ran","syntology_url":"https://syntology.ai/paper/2104.12820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12820"}},"official":{"repos":["yashchandak/UnO"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarks-for-deep-off-policy-evaluation-1","slug":"benchmarks-for-deep-off-policy-evaluation-1","title":"Benchmarks for Deep Off-Policy Evaluation","date":"2021-03-30","arxiv_id":"2103.16596","repositories_listed":3,"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":3,"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/benchmarks-for-deep-off-policy-evaluation-1#ran","syntology_url":"https://syntology.ai/paper/2103.16596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16596"}},"official":{"repos":["google-research/deep_ope"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-large-scale-open-dataset-for-bandit","slug":"a-large-scale-open-dataset-for-bandit","title":"Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation","date":"2020-08-17","arxiv_id":"2008.07146","repositories_listed":4,"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":0,"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/a-large-scale-open-dataset-for-bandit#ran","syntology_url":"https://syntology.ai/paper/2008.07146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.07146"}},"official":{"repos":["st-tech/zr-obp"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/strictly-batch-imitation-learning-by-energy","slug":"strictly-batch-imitation-learning-by-energy","title":"Strictly Batch Imitation Learning by Energy-based Distribution Matching","date":"2020-06-25","arxiv_id":"2006.14154","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":5,"n_ran_checked":14,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":1,"phrase":"16 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/strictly-batch-imitation-learning-by-energy#ran","syntology_url":"https://syntology.ai/paper/2006.14154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.14154"}},"official":{"repos":["vanderschaarlab/mlforhealthlabpub"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/confident-off-policy-evaluation-and-selection","slug":"confident-off-policy-evaluation-and-selection","title":"Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting","date":"2020-06-18","arxiv_id":"2006.10460","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/confident-off-policy-evaluation-and-selection#ran","syntology_url":"https://syntology.ai/paper/2006.10460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10460"}},"official":{"repos":["deepmind/offpolicy_selection_eslb"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/off-policy-evaluation-and-learning-for","slug":"off-policy-evaluation-and-learning-for","title":"Off-Policy Evaluation and Learning for External Validity under a Covariate Shift","date":"2020-02-26","arxiv_id":"2002.11642","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/off-policy-evaluation-and-learning-for#ran","syntology_url":"https://syntology.ai/paper/2002.11642","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.11642"}},"official":{"repos":["MasaKat0/OPE_CS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/counterfactual-off-policy-evaluation-with","slug":"counterfactual-off-policy-evaluation-with","title":"Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models","date":"2019-05-14","arxiv_id":"1905.05824","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":0,"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/counterfactual-off-policy-evaluation-with#ran","syntology_url":"https://syntology.ai/paper/1905.05824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05824"}},"official":{"repos":["clinicalml/gumbel-max-scm"],"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/importance-sampling-policy-evaluation-with-an","slug":"importance-sampling-policy-evaluation-with-an","title":"Importance Sampling Policy Evaluation with an Estimated Behavior Policy","date":"2018-06-04","arxiv_id":"1806.01347","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/importance-sampling-policy-evaluation-with-an#ran","syntology_url":"https://syntology.ai/paper/1806.01347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.01347"}},"official":{"repos":["LARG/regression-importance-sampling"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/off-policy-evaluation-for-slate","slug":"off-policy-evaluation-for-slate","title":"Off-policy evaluation for slate recommendation","date":"2016-05-16","arxiv_id":"1605.04812","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/off-policy-evaluation-for-slate#ran","syntology_url":"https://syntology.ai/paper/1605.04812","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.04812"}},"official":{"repos":["adith387/slates_semisynth_expts"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"2e6ea2d0f7d18328f89390441d431e86f3308d7bf5593aeaa3028bea8ff2d214","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}