{"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/efficient-exploration/papers/ran/1","list_of":"/task/efficient-exploration","task":"Efficient Exploration","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":[1,57],"of":57,"counts":{"archive_papers_tagged":514,"with_a_code_link":189,"where_syntology_ran_a_sample":57,"not_listed_spam_title":0,"listed":514,"listed_where_code_ran":57,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":48,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":48,"listed_every_run_a_failure_of_syntologys_instrument":9,"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/efficient-exploration/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/fragfm-efficient-fragment-based-molecular","slug":"fragfm-efficient-fragment-based-molecular","title":"FragFM: Hierarchical Framework for Efficient Molecule Generation via Fragment-Level Discrete Flow Matching","date":"2025-02-19","arxiv_id":"2502.15805","repositories_listed":0,"syntology":{"n":14,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"8 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; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/fragfm-efficient-fragment-based-molecular#ran","syntology_url":"https://syntology.ai/paper/2502.15805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.15805"}},"official":null}},{"url":"/paper/maximum-entropy-reinforcement-learning-with-1","slug":"maximum-entropy-reinforcement-learning-with-1","title":"Maximum Entropy Reinforcement Learning with Diffusion Policy","date":"2025-02-17","arxiv_id":"2502.11612","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":13,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/maximum-entropy-reinforcement-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/2502.11612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11612"}},"official":{"repos":["diffusionyes/maxentdp"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":6,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/langevin-soft-actor-critic-efficient","slug":"langevin-soft-actor-critic-efficient","title":"Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning","date":"2025-01-29","arxiv_id":"2501.17827","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":1,"n_ran_checked":3,"n_instrument":3,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/langevin-soft-actor-critic-efficient#ran","syntology_url":"https://syntology.ai/paper/2501.17827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.17827"}},"official":{"repos":["hmishfaq/lsac"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-skills-from-unlabeled-prior-data","slug":"leveraging-skills-from-unlabeled-prior-data","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","date":"2024-10-23","arxiv_id":"2410.18076","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/leveraging-skills-from-unlabeled-prior-data#ran","syntology_url":"https://syntology.ai/paper/2410.18076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18076"}},"official":{"repos":["rail-berkeley/supe"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llama-berry-pairwise-optimization-for-o1-like","slug":"llama-berry-pairwise-optimization-for-o1-like","title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","date":"2024-10-03","arxiv_id":"2410.02884","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llama-berry-pairwise-optimization-for-o1-like#ran","syntology_url":"https://syntology.ai/paper/2410.02884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02884"}},"official":null}},{"url":"/paper/adaptive-teachers-for-amortized-samplers","slug":"adaptive-teachers-for-amortized-samplers","title":"Adaptive teachers for amortized samplers","date":"2024-10-02","arxiv_id":"2410.01432","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptive-teachers-for-amortized-samplers#ran","syntology_url":"https://syntology.ai/paper/2410.01432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01432"}},"official":{"repos":["alstn12088/adaptive-teacher"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-foundation-models-for-online","slug":"adaptive-foundation-models-for-online","title":"Scalable Exploration via Ensemble++","date":"2024-07-18","arxiv_id":"2407.13195","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":1,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/adaptive-foundation-models-for-online#ran","syntology_url":"https://syntology.ai/paper/2407.13195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13195"}},"official":{"repos":["szrlee/GPT-HyperAgent","szrlee/ensemble_plus_plus"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-exploration-in-average-reward","slug":"efficient-exploration-in-average-reward","title":"Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling","date":"2024-05-29","arxiv_id":"2405.19017","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":2,"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 2 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/efficient-exploration-in-average-reward#ran","syntology_url":"https://syntology.ai/paper/2405.19017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19017"}},"official":{"repos":["danilprov/cmdp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/navigating-chemical-space-with-latent-flows","slug":"navigating-chemical-space-with-latent-flows","title":"Navigating Chemical Space with Latent Flows","date":"2024-05-07","arxiv_id":"2405.03987","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":6,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/navigating-chemical-space-with-latent-flows#ran","syntology_url":"https://syntology.ai/paper/2405.03987","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.03987"}},"official":{"repos":["garywei944/chemflow"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/streamlining-ocean-dynamics-modeling-with","slug":"streamlining-ocean-dynamics-modeling-with","title":"Streamlining Ocean Dynamics Modeling with Fourier Neural Operators: A Multiobjective Hyperparameter and Architecture Optimization Approach","date":"2024-04-07","arxiv_id":"2404.05768","repositories_listed":2,"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":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) · 1 unverified","sample_list":"/paper/streamlining-ocean-dynamics-modeling-with#ran","syntology_url":"https://syntology.ai/paper/2404.05768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05768"}},"official":null}},{"url":"/paper/mamba-an-effective-world-model-approach-for","slug":"mamba-an-effective-world-model-approach-for","title":"MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning","date":"2024-03-14","arxiv_id":"2403.09859","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mamba-an-effective-world-model-approach-for#ran","syntology_url":"https://syntology.ai/paper/2403.09859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09859"}},"official":{"repos":["zoharri/mamba"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/scalable-online-exploration-via-coverability","slug":"scalable-online-exploration-via-coverability","title":"Scalable Online Exploration via Coverability","date":"2024-03-11","arxiv_id":"2403.06571","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scalable-online-exploration-via-coverability#ran","syntology_url":"https://syntology.ai/paper/2403.06571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06571"}},"official":{"repos":["philip-amortila/l1-coverability"],"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/efficient-low-rank-matrix-estimation","slug":"efficient-low-rank-matrix-estimation","title":"Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits","date":"2024-02-17","arxiv_id":"2402.11156","repositories_listed":1,"syntology":{"n":16,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/efficient-low-rank-matrix-estimation#ran","syntology_url":"https://syntology.ai/paper/2402.11156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11156"}},"official":{"repos":["jajajang/lowpopart"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/noise-adaptive-confidence-sets-for-linear","slug":"noise-adaptive-confidence-sets-for-linear","title":"Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization","date":"2024-02-12","arxiv_id":"2402.07341","repositories_listed":1,"syntology":{"n":15,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/noise-adaptive-confidence-sets-for-linear#ran","syntology_url":"https://syntology.ai/paper/2402.07341","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07341"}},"official":{"repos":["jungtaekkim/losan-lofav"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/iterated-denoising-energy-matching-for","slug":"iterated-denoising-energy-matching-for","title":"Iterated Denoising Energy Matching for Sampling from Boltzmann Densities","date":"2024-02-09","arxiv_id":"2402.06121","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":3,"n_ran_checked":3,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/iterated-denoising-energy-matching-for#ran","syntology_url":"https://syntology.ai/paper/2402.06121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06121"}},"official":{"repos":["jarridrb/dem"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-es-gradient-free-planning-with","slug":"diffusion-es-gradient-free-planning-with","title":"Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following","date":"2024-02-09","arxiv_id":"2402.06559","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":12,"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) · 2 unverified","sample_list":"/paper/diffusion-es-gradient-free-planning-with#ran","syntology_url":"https://syntology.ai/paper/2402.06559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06559"}},"official":{"repos":["bhyang/diffusion-es"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-sober-look-at-llms-for-material-discovery","slug":"a-sober-look-at-llms-for-material-discovery","title":"A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?","date":"2024-02-07","arxiv_id":"2402.05015","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-sober-look-at-llms-for-material-discovery#ran","syntology_url":"https://syntology.ai/paper/2402.05015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05015"}},"official":{"repos":["wiseodd/lapeft-bayesopt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ltu-ili-an-all-in-one-framework-for-implicit","slug":"ltu-ili-an-all-in-one-framework-for-implicit","title":"LtU-ILI: An All-in-One Framework for Implicit Inference in Astrophysics and Cosmology","date":"2024-02-06","arxiv_id":"2402.05137","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/ltu-ili-an-all-in-one-framework-for-implicit#ran","syntology_url":"https://syntology.ai/paper/2402.05137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05137"}},"official":{"repos":["maho3/ltu-ili"],"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/hyperagent-a-simple-scalable-efficient-and","slug":"hyperagent-a-simple-scalable-efficient-and","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","date":"2024-02-05","arxiv_id":"2402.10228","repositories_listed":3,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/hyperagent-a-simple-scalable-efficient-and#ran","syntology_url":"https://syntology.ai/paper/2402.10228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10228"}},"official":{"repos":["szrlee/hyperagent"],"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"]}}},{"url":"/paper/optimizing-protein-fitness-using-gibbs","slug":"optimizing-protein-fitness-using-gibbs","title":"Improving Protein Optimization with Smoothed Fitness Landscapes","date":"2023-07-02","arxiv_id":"2307.00494","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":3,"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 3 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; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/optimizing-protein-fitness-using-gibbs#ran","syntology_url":"https://syntology.ai/paper/2307.00494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.00494"}},"official":{"repos":["kirjner/ggs"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tuning-legged-locomotion-controllers-via-safe","slug":"tuning-legged-locomotion-controllers-via-safe","title":"Tuning Legged Locomotion Controllers via Safe Bayesian Optimization","date":"2023-06-12","arxiv_id":"2306.07092","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/tuning-legged-locomotion-controllers-via-safe#ran","syntology_url":"https://syntology.ai/paper/2306.07092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.07092"}},"official":{"repos":["lasgroup/gosafeopt"],"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/provable-and-practical-efficient-exploration","slug":"provable-and-practical-efficient-exploration","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","date":"2023-05-29","arxiv_id":"2305.18246","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/provable-and-practical-efficient-exploration#ran","syntology_url":"https://syntology.ai/paper/2305.18246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18246"}},"official":{"repos":["hmishfaq/lmc-lsvi"],"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/exploring-through-random-curiosity-with","slug":"exploring-through-random-curiosity-with","title":"Exploring through Random Curiosity with General Value Functions","date":"2022-11-18","arxiv_id":"2211.10282","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/exploring-through-random-curiosity-with#ran","syntology_url":"https://syntology.ai/paper/2211.10282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10282"}},"official":{"repos":["aditya-ramesh-10/exploring-through-rcgvf"],"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/leco-learnable-episodic-count-for-task","slug":"leco-learnable-episodic-count-for-task","title":"LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward","date":"2022-10-11","arxiv_id":"2210.05409","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":1,"n_ran_checked":1,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":10,"phrase":"7 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; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/leco-learnable-episodic-count-for-task#ran","syntology_url":"https://syntology.ai/paper/2210.05409","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.05409"}},"official":{"repos":["kakaobrain/leco"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/incremental-3d-scene-completion-for-safe-and","slug":"incremental-3d-scene-completion-for-safe-and","title":"SC-Explorer: Incremental 3D Scene Completion for Safe and Efficient Exploration Mapping and Planning","date":"2022-08-17","arxiv_id":"2208.08307","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":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) · 1 unverified","sample_list":"/paper/incremental-3d-scene-completion-for-safe-and#ran","syntology_url":"https://syntology.ai/paper/2208.08307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.08307"}},"official":{"repos":["ethz-asl/ssc_exploration"],"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/a-langevin-like-sampler-for-discrete","slug":"a-langevin-like-sampler-for-discrete","title":"A Langevin-like Sampler for Discrete Distributions","date":"2022-06-20","arxiv_id":"2206.09914","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-langevin-like-sampler-for-discrete#ran","syntology_url":"https://syntology.ai/paper/2206.09914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.09914"}},"official":{"repos":["ruqizhang/discrete-langevin"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/static-scheduling-with-predictions-learned","slug":"static-scheduling-with-predictions-learned","title":"On Preemption and Learning in Stochastic Scheduling","date":"2022-05-31","arxiv_id":"2205.15695","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/static-scheduling-with-predictions-learned#ran","syntology_url":"https://syntology.ai/paper/2205.15695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.15695"}},"official":{"repos":["hugorichard/ml4a-scheduling"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-from-self-sampled-correct-and","slug":"learning-from-self-sampled-correct-and","title":"Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions","date":"2022-05-28","arxiv_id":"2205.14318","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-from-self-sampled-correct-and#ran","syntology_url":"https://syntology.ai/paper/2205.14318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14318"}},"official":{"repos":["microsoft/tracecodegen"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-solve-combinatorial-graph","slug":"learning-to-solve-combinatorial-graph","title":"Learning to Solve Combinatorial Graph Partitioning Problems via Efficient Exploration","date":"2022-05-27","arxiv_id":"2205.14105","repositories_listed":1,"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":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) · 2 unverified","sample_list":"/paper/learning-to-solve-combinatorial-graph#ran","syntology_url":"https://syntology.ai/paper/2205.14105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14105"}},"official":{"repos":["tomdbar/ecord"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/think-global-act-local-dual-scale-graph","slug":"think-global-act-local-dual-scale-graph","title":"Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation","date":"2022-02-23","arxiv_id":"2202.11742","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/think-global-act-local-dual-scale-graph#ran","syntology_url":"https://syntology.ai/paper/2202.11742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.11742"}},"official":null}},{"url":"/paper/online-decision-transformer","slug":"online-decision-transformer","title":"Online Decision Transformer","date":"2022-02-11","arxiv_id":"2202.05607","repositories_listed":2,"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/online-decision-transformer#ran","syntology_url":"https://syntology.ai/paper/2202.05607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.05607"}},"official":{"repos":["facebookresearch/online-dt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"url":"/paper/learning-to-act-with-affordance-aware-1","slug":"learning-to-act-with-affordance-aware-1","title":"Learning to Act with Affordance-Aware Multimodal Neural SLAM","date":"2022-01-24","arxiv_id":"2201.09862","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":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/learning-to-act-with-affordance-aware-1#ran","syntology_url":"https://syntology.ai/paper/2201.09862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.09862"}},"official":{"repos":["amazon-research/multimodal-neuralslam"],"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/successor-feature-landmarks-for-long-horizon","slug":"successor-feature-landmarks-for-long-horizon","title":"Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning","date":"2021-11-18","arxiv_id":"2111.09858","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/successor-feature-landmarks-for-long-horizon#ran","syntology_url":"https://syntology.ai/paper/2111.09858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09858"}},"official":null}},{"url":"/paper/heterogeneous-multi-player-multi-armed","slug":"heterogeneous-multi-player-multi-armed","title":"Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization","date":"2021-10-27","arxiv_id":"2110.14622","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/heterogeneous-multi-player-multi-armed#ran","syntology_url":"https://syntology.ai/paper/2110.14622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14622"}},"official":{"repos":["shengroup/mpmab_beacon"],"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/landmark-guided-subgoal-generation-in","slug":"landmark-guided-subgoal-generation-in","title":"Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning","date":"2021-10-26","arxiv_id":"2110.13625","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/landmark-guided-subgoal-generation-in#ran","syntology_url":"https://syntology.ai/paper/2110.13625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13625"}},"official":{"repos":["junsu-kim97/higl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-skills-for-efficient-exploration","slug":"hierarchical-skills-for-efficient-exploration","title":"Hierarchical Skills for Efficient Exploration","date":"2021-10-20","arxiv_id":"2110.10809","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":7,"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/hierarchical-skills-for-efficient-exploration#ran","syntology_url":"https://syntology.ai/paper/2110.10809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.10809"}},"official":{"repos":["facebookresearch/hsd3"],"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/principled-exploration-via-optimistic","slug":"principled-exploration-via-optimistic","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","date":"2021-05-13","arxiv_id":"2105.06022","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":12,"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) · 6 unverified","sample_list":"/paper/principled-exploration-via-optimistic#ran","syntology_url":"https://syntology.ai/paper/2105.06022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.06022"}},"official":{"repos":["Baichenjia/OB2I"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/online-limited-memory-neural-linear-bandits-1","slug":"online-limited-memory-neural-linear-bandits-1","title":"Online Limited Memory Neural-Linear Bandits with Likelihood Matching","date":"2021-02-07","arxiv_id":"2102.03799","repositories_listed":3,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/online-limited-memory-neural-linear-bandits-1#ran","syntology_url":"https://syntology.ai/paper/2102.03799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.03799"}},"official":null}},{"url":"/paper/efficient-exploration-for-model-based-1","slug":"efficient-exploration-for-model-based-1","title":"Model-based Reinforcement Learning for Continuous Control with Posterior Sampling","date":"2020-11-20","arxiv_id":"2012.09613","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/efficient-exploration-for-model-based-1#ran","syntology_url":"https://syntology.ai/paper/2012.09613","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.09613"}},"official":{"repos":["yingfan-bot/mbpsrl"],"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/latent-world-models-for-intrinsically","slug":"latent-world-models-for-intrinsically","title":"Latent World Models For Intrinsically Motivated Exploration","date":"2020-10-05","arxiv_id":"2010.02302","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":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) · 2 unverified","sample_list":"/paper/latent-world-models-for-intrinsically#ran","syntology_url":"https://syntology.ai/paper/2010.02302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02302"}},"official":{"repos":["htdt/lwm"],"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/novelty-search-in-representational-space-for","slug":"novelty-search-in-representational-space-for","title":"Novelty Search in Representational Space for Sample Efficient Exploration","date":"2020-09-28","arxiv_id":"2009.13579","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":0,"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/novelty-search-in-representational-space-for#ran","syntology_url":"https://syntology.ai/paper/2009.13579","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.13579"}},"official":{"repos":["taodav/nsrs"],"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/occupancy-anticipation-for-efficient","slug":"occupancy-anticipation-for-efficient","title":"Occupancy Anticipation for Efficient Exploration and Navigation","date":"2020-08-21","arxiv_id":"2008.09285","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/occupancy-anticipation-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2008.09285","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.09285"}},"official":{"repos":["facebookresearch/OccupancyAnticipation"],"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/see-hear-explore-curiosity-via-audio-visual","slug":"see-hear-explore-curiosity-via-audio-visual","title":"See, Hear, Explore: Curiosity via Audio-Visual Association","date":"2020-07-07","arxiv_id":"2007.03669","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/see-hear-explore-curiosity-via-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2007.03669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.03669"}},"official":{"repos":["vdean/audio-curiosity"],"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/hierarchically-organized-latent-modules-for","slug":"hierarchically-organized-latent-modules-for","title":"Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems","date":"2020-07-02","arxiv_id":"2007.01195","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hierarchically-organized-latent-modules-for#ran","syntology_url":"https://syntology.ai/paper/2007.01195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.01195"}},"official":{"repos":["flowersteam/holmes"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learn-to-effectively-explore-in-context-based","slug":"learn-to-effectively-explore-in-context-based","title":"MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration","date":"2020-06-15","arxiv_id":"2006.08170","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/learn-to-effectively-explore-in-context-based#ran","syntology_url":"https://syntology.ai/paper/2006.08170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.08170"}},"official":{"repos":["NagisaZj/MetaCURE-Public"],"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/optimistic-exploration-even-with-a-1","slug":"optimistic-exploration-even-with-a-1","title":"Optimistic Exploration even with a Pessimistic Initialisation","date":"2020-02-26","arxiv_id":"2002.12174","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/optimistic-exploration-even-with-a-1#ran","syntology_url":"https://syntology.ai/paper/2002.12174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12174"}},"official":{"repos":["oxwhirl/opiq"],"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/meta-reinforcement-learning-with-autonomous-1","slug":"meta-reinforcement-learning-with-autonomous-1","title":"Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies","date":"2020-01-01","arxiv_id":"2001.00248","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meta-reinforcement-learning-with-autonomous-1#ran","syntology_url":"https://syntology.ai/paper/2001.00248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.00248"}},"official":{"repos":["srsohn/msgi"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/estimating-risk-and-uncertainty-in-deep","slug":"estimating-risk-and-uncertainty-in-deep","title":"Estimating Risk and Uncertainty in Deep Reinforcement Learning","date":"2019-05-23","arxiv_id":"1905.09638","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/estimating-risk-and-uncertainty-in-deep#ran","syntology_url":"https://syntology.ai/paper/1905.09638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09638"}},"official":{"repos":["IndustAI/risk-and-uncertainty"],"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/efficient-off-policy-meta-reinforcement","slug":"efficient-off-policy-meta-reinforcement","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","date":"2019-03-19","arxiv_id":"1903.08254","repositories_listed":7,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":5,"phrase":"8 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficient-off-policy-meta-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1903.08254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.08254"}},"official":{"repos":["katerakelly/oyster"],"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/model-based-active-exploration","slug":"model-based-active-exploration","title":"Model-Based Active Exploration","date":"2018-10-29","arxiv_id":"1810.12162","repositories_listed":2,"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/model-based-active-exploration#ran","syntology_url":"https://syntology.ai/paper/1810.12162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.12162"}},"official":{"repos":["nnaisense/max"],"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/cm3-cooperative-multi-goal-multi-stage-multi","slug":"cm3-cooperative-multi-goal-multi-stage-multi","title":"CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning","date":"2018-09-13","arxiv_id":"1809.05188","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/cm3-cooperative-multi-goal-multi-stage-multi#ran","syntology_url":"https://syntology.ai/paper/1809.05188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.05188"}},"official":{"repos":["011235813/cm3"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/count-based-exploration-with-the-successor","slug":"count-based-exploration-with-the-successor","title":"Count-Based Exploration with the Successor Representation","date":"2018-07-31","arxiv_id":"1807.11622","repositories_listed":2,"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":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) · 1 unverified","sample_list":"/paper/count-based-exploration-with-the-successor#ran","syntology_url":"https://syntology.ai/paper/1807.11622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.11622"}},"official":{"repos":["mcmachado/count_based_exploration_sr"],"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/variance-networks-when-expectation-does-not","slug":"variance-networks-when-expectation-does-not","title":"Variance Networks: When Expectation Does Not Meet Your Expectations","date":"2018-03-10","arxiv_id":"1803.03764","repositories_listed":2,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/variance-networks-when-expectation-does-not#ran","syntology_url":"https://syntology.ai/paper/1803.03764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.03764"}},"official":{"repos":["da-molchanov/variance-networks"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/noisy-networks-for-exploration","slug":"noisy-networks-for-exploration","title":"Noisy Networks for Exploration","date":"2017-06-30","arxiv_id":"1706.10295","repositories_listed":15,"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/noisy-networks-for-exploration#ran","syntology_url":"https://syntology.ai/paper/1706.10295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.10295"}},"official":null}},{"url":"/paper/automatic-chemical-design-using-a-data-driven","slug":"automatic-chemical-design-using-a-data-driven","title":"Automatic chemical design using a data-driven continuous representation of molecules","date":"2016-10-07","arxiv_id":"1610.02415","repositories_listed":11,"syntology":{"n":26,"n_ran":17,"n_constructed":1,"n_ran_checked":14,"n_instrument":3,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":7,"phrase":"17 ran (of which 1 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/automatic-chemical-design-using-a-data-driven#ran","syntology_url":"https://syntology.ai/paper/1610.02415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.02415"}},"official":{"repos":["HIPS/molecule-autoencoder","aspuru-guzik-group/chemical_vae"],"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":["listed","official"]}}},{"url":"/paper/deep-exploration-via-bootstrapped-dqn","slug":"deep-exploration-via-bootstrapped-dqn","title":"Deep Exploration via Bootstrapped DQN","date":"2016-02-15","arxiv_id":"1602.04621","repositories_listed":6,"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/deep-exploration-via-bootstrapped-dqn#ran","syntology_url":"https://syntology.ai/paper/1602.04621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.04621"}},"official":null}},{"url":"/paper/stochastic-gradient-hamiltonian-monte-carlo","slug":"stochastic-gradient-hamiltonian-monte-carlo","title":"Stochastic Gradient Hamiltonian Monte Carlo","date":"2014-02-17","arxiv_id":"1402.4102","repositories_listed":7,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/stochastic-gradient-hamiltonian-monte-carlo#ran","syntology_url":"https://syntology.ai/paper/1402.4102","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1402.4102"}},"official":null}}],"record_sha256":"b113c30fc4a979049a2b6fffaf8c61b205210c4188d88d56f4b899ba0783015f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}