{"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":"/method/reinforce/papers/ran/1","list_of":"/method/reinforce","method":"REINFORCE","archive":{"snapshot":"2025-07-28"},"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 isolate this method inside it.","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":[1,24],"of":24,"counts":{"archive_papers_tagged":185,"with_a_code_link":80,"where_syntology_ran_a_sample":24,"not_listed_spam_title":0,"listed":185,"listed_where_code_ran":24,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":20,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":20,"listed_every_run_a_failure_of_syntologys_instrument":4,"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":"/method/reinforce/papers/ran/1","prev":null,"next":null,"papers":[{"paper":"/paper/finding-visual-task-vectors","slug":"finding-visual-task-vectors","title":"Finding Visual Task Vectors","date":"2024-04-08","arxiv_id":"2404.05729","n_code_links":1,"syntology":{"ran":2,"of":11,"n_ran_checked":0,"n_instrument":2,"unverified":9,"pointer_only":11,"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) · 9 unverified","official":{"repos":["alhojel/visual_task_vectors"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/re3val-reinforced-and-reranked-generative","slug":"re3val-reinforced-and-reranked-generative","title":"Re3val: Reinforced and Reranked Generative Retrieval","date":"2024-01-30","arxiv_id":"2401.16979","n_code_links":0,"syntology":{"ran":10,"of":13,"n_ran_checked":8,"n_instrument":2,"unverified":3,"pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/remax-a-simple-effective-and-efficient-method","slug":"remax-a-simple-effective-and-efficient-method","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","date":"2023-10-16","arxiv_id":"2310.10505","n_code_links":3,"syntology":{"ran":11,"of":13,"n_ran_checked":10,"n_instrument":1,"unverified":2,"pointer_only":13,"phrase":"11 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["liziniu/ReMax"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/esrl-efficient-sampling-based-reinforcement","slug":"esrl-efficient-sampling-based-reinforcement","title":"ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation","date":"2023-08-04","arxiv_id":"2308.02223","n_code_links":2,"syntology":{"ran":12,"of":14,"n_ran_checked":11,"n_instrument":1,"unverified":2,"pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["wangclnlp/DeepSpeed-Chat-Extension"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/generalizing-few-shot-nas-with-gradient-1","slug":"generalizing-few-shot-nas-with-gradient-1","title":"Generalizing Few-Shot NAS with Gradient Matching","date":"2022-03-29","arxiv_id":"2203.15207","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["skhu101/GM-NAS"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/gradient-estimation-with-discrete-stein","slug":"gradient-estimation-with-discrete-stein","title":"Gradient Estimation with Discrete Stein Operators","date":"2022-02-19","arxiv_id":"2202.09497","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["thjashin/rodeo"],"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"]}}},{"paper":"/paper/double-control-variates-for-gradient","slug":"double-control-variates-for-gradient","title":"Double Control Variates for Gradient Estimation in Discrete Latent Variable Models","date":"2021-11-09","arxiv_id":"2111.05300","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"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","official":{"repos":["thjashin/double-cv"],"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"]}}},{"paper":"/paper/regen-reinforcement-learning-for-text-and","slug":"regen-reinforcement-learning-for-text-and","title":"ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models","date":"2021-08-27","arxiv_id":"2108.12472","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["IBM/regen"],"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"]}}},{"paper":"/paper/arms-antithetic-reinforce-multi-sample","slug":"arms-antithetic-reinforce-multi-sample","title":"ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables","date":"2021-05-28","arxiv_id":"2105.14141","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["alekdimi/arms"],"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"]}}},{"paper":"/paper/pomo-policy-optimization-with-multiple-optima","slug":"pomo-policy-optimization-with-multiple-optima","title":"POMO: Policy Optimization with Multiple Optima for Reinforcement Learning","date":"2020-10-30","arxiv_id":"2010.16011","n_code_links":3,"syntology":{"ran":1,"of":8,"n_ran_checked":1,"n_instrument":0,"unverified":7,"pointer_only":8,"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) · 7 unverified","official":{"repos":["yd-kwon/POMO"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/confuciux-autonomous-hardware-resource","slug":"confuciux-autonomous-hardware-resource","title":"ConfuciuX: Autonomous Hardware Resource Assignment for DNN Accelerators using Reinforcement Learning","date":"2020-09-04","arxiv_id":"2009.02010","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["maestro-project/confuciux"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/angle-based-search-space-shrinking-for-neural","slug":"angle-based-search-space-shrinking-for-neural","title":"Angle-based Search Space Shrinking for Neural Architecture Search","date":"2020-04-28","arxiv_id":"2004.13431","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/guided-dialog-policy-learning-without","slug":"guided-dialog-policy-learning-without","title":"Guided Dialog Policy Learning without Adversarial Learning in the Loop","date":"2020-04-07","arxiv_id":"2004.03267","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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","official":{"repos":["cszmli/dp-without-adv"],"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":["unlocated"]}}},{"paper":"/paper/a-hybrid-stochastic-policy-gradient-algorithm","slug":"a-hybrid-stochastic-policy-gradient-algorithm","title":"A Hybrid Stochastic Policy Gradient Algorithm for Reinforcement Learning","date":"2020-03-01","arxiv_id":"2003.00430","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["unc-optimization/ProxHSPGA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/neural-predictor-for-neural-architecture","slug":"neural-predictor-for-neural-architecture","title":"Neural Predictor for Neural Architecture Search","date":"2019-12-02","arxiv_id":"1912.00848","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":null}},{"paper":"/paper/exploiting-uncertainty-of-loss-landscape-for","slug":"exploiting-uncertainty-of-loss-landscape-for","title":"Exploiting Uncertainty of Loss Landscape for Stochastic Optimization","date":"2019-05-30","arxiv_id":"1905.13200","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["bsvineethiitg/adams"],"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"]}}},{"paper":"/paper/interpretable-neural-predictions-with","slug":"interpretable-neural-predictions-with","title":"Interpretable Neural Predictions with Differentiable Binary Variables","date":"2019-05-20","arxiv_id":"1905.08160","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","official":{"repos":["bastings/interpretable_predictions"],"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"]}}},{"paper":"/paper/arsm-augment-reinforce-swap-merge-estimator","slug":"arsm-augment-reinforce-swap-merge-estimator","title":"ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables","date":"2019-05-04","arxiv_id":"1905.01413","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ARM-gradient/ARSM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/proxylessnas-direct-neural-architecture","slug":"proxylessnas-direct-neural-architecture","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","date":"2018-12-02","arxiv_id":"1812.00332","n_code_links":23,"syntology":{"ran":17,"of":27,"n_ran_checked":14,"n_instrument":3,"unverified":10,"pointer_only":4,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","official":{"repos":["MIT-HAN-LAB/ProxylessNAS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/learning-scheduling-algorithms-for-data","slug":"learning-scheduling-algorithms-for-data","title":"Learning Scheduling Algorithms for Data Processing Clusters","date":"2018-10-03","arxiv_id":"1810.01963","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["hongzimao/decima-sim"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/attention-learn-to-solve-routing-problems","slug":"attention-learn-to-solve-routing-problems","title":"Attention, Learn to Solve Routing Problems!","date":"2018-03-22","arxiv_id":"1803.08475","n_code_links":15,"syntology":{"ran":27,"of":40,"n_ran_checked":20,"n_instrument":7,"unverified":13,"pointer_only":5,"phrase":"27 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 7 where Syntology's instrument failed) · 13 unverified","official":{"repos":["wouterkool/attention-tsp","wouterkool/attention-learn-to-route"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/action-depedent-control-variates-for-policy","slug":"action-depedent-control-variates-for-policy","title":"Action-depedent Control Variates for Policy Optimization via Stein's Identity","date":"2017-10-30","arxiv_id":"1710.11198","n_code_links":2,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":null}},{"paper":"/paper/inferring-and-executing-programs-for-visual","slug":"inferring-and-executing-programs-for-visual","title":"Inferring and Executing Programs for Visual Reasoning","date":"2017-05-10","arxiv_id":"1705.03633","n_code_links":5,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["facebookresearch/clevr-iep"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/self-critical-sequence-training-for-image","slug":"self-critical-sequence-training-for-image","title":"Self-critical Sequence Training for Image Captioning","date":"2016-12-02","arxiv_id":"1612.00563","n_code_links":31,"syntology":{"ran":12,"of":13,"n_ran_checked":5,"n_instrument":7,"unverified":1,"pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified","official":null}}],"record_sha256":"a119102bff259c056bbd92109e33309ce39361f735bde13a3b5194fcc109cfb4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}