{"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/reinforcement-learning-2/papers/17","list_of":"/task/reinforcement-learning-2","task":"reinforcement-learning","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":17,"pages_in_order":135,"rows_per_page":100,"rows":[1601,1700],"of":13427,"counts":{"archive_papers_tagged":13427,"with_a_code_link":4119,"where_syntology_ran_a_sample":1165,"not_listed_spam_title":0,"listed":13427,"listed_where_code_ran":1165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":973,"every_run_a_failure_of_syntologys_instrument":192,"listed_with_a_run_with_no_instrument_failure":973,"listed_every_run_a_failure_of_syntologys_instrument":192,"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/reinforcement-learning-2","prev":"/task/reinforcement-learning-2/papers/16","next":"/task/reinforcement-learning-2/papers/18","papers":[{"url":"/paper/amago-scalable-in-context-reinforcement","slug":"amago-scalable-in-context-reinforcement","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","date":"2023-10-15","arxiv_id":"2310.09971","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/amago-scalable-in-context-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2310.09971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09971"}},"official":{"repos":["ut-austin-rpl/amago"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/specialized-deep-residual-policy-safe","slug":"specialized-deep-residual-policy-safe","title":"Specialized Deep Residual Policy Safe Reinforcement Learning-Based Controller for Complex and Continuous State-Action Spaces","date":"2023-10-15","arxiv_id":"2310.14788","repositories_listed":1,"syntology":null},{"url":"/paper/storm-efficient-stochastic-transformer-based-1","slug":"storm-efficient-stochastic-transformer-based-1","title":"STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning","date":"2023-10-14","arxiv_id":"2310.09615","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"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) · 2 unverified","sample_list":"/paper/storm-efficient-stochastic-transformer-based-1#ran","syntology_url":"https://syntology.ai/paper/2310.09615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09615"}},"official":{"repos":["weipu-zhang/storm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/impact-of-multi-armed-bandit-strategies-on","slug":"impact-of-multi-armed-bandit-strategies-on","title":"Dealing with uncertainty: balancing exploration and exploitation in deep recurrent reinforcement learning","date":"2023-10-12","arxiv_id":"2310.08331","repositories_listed":1,"syntology":null},{"url":"/paper/transformers-as-decision-makers-provable-in","slug":"transformers-as-decision-makers-provable-in","title":"Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining","date":"2023-10-12","arxiv_id":"2310.08566","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/transformers-as-decision-makers-provable-in#ran","syntology_url":"https://syntology.ai/paper/2310.08566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08566"}},"official":{"repos":["licong-lin/in-context-rl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/universal-visual-decomposer-long-horizon","slug":"universal-visual-decomposer-long-horizon","title":"Universal Visual Decomposer: Long-Horizon Manipulation Made Easy","date":"2023-10-12","arxiv_id":"2310.08581","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/universal-visual-decomposer-long-horizon#ran","syntology_url":"https://syntology.ai/paper/2310.08581","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08581"}},"official":null}},{"url":"/paper/virtual-augmented-reality-for-atari","slug":"virtual-augmented-reality-for-atari","title":"Virtual Augmented Reality for Atari Reinforcement Learning","date":"2023-10-12","arxiv_id":"2310.08683","repositories_listed":1,"syntology":null},{"url":"/paper/cheap-talking-algorithms","slug":"cheap-talking-algorithms","title":"Cheap Talking Algorithms","date":"2023-10-11","arxiv_id":"2310.07867","repositories_listed":1,"syntology":null},{"url":"/paper/imitation-learning-from-observation-with","slug":"imitation-learning-from-observation-with","title":"Imitation Learning from Observation with Automatic Discount Scheduling","date":"2023-10-11","arxiv_id":"2310.07433","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":4,"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) · 0 unverified","sample_list":"/paper/imitation-learning-from-observation-with#ran","syntology_url":"https://syntology.ai/paper/2310.07433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07433"}},"official":null}},{"url":"/paper/revisiting-plasticity-in-visual-reinforcement","slug":"revisiting-plasticity-in-visual-reinforcement","title":"Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages","date":"2023-10-11","arxiv_id":"2310.07418","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"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) · 2 unverified","sample_list":"/paper/revisiting-plasticity-in-visual-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2310.07418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07418"}},"official":{"repos":["Guozheng-Ma/Adaptive-Replay-Ratio"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/roboclip-one-demonstration-is-enough-to-learn","slug":"roboclip-one-demonstration-is-enough-to-learn","title":"RoboCLIP: One Demonstration is Enough to Learn Robot Policies","date":"2023-10-11","arxiv_id":"2310.07899","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/roboclip-one-demonstration-is-enough-to-learn#ran","syntology_url":"https://syntology.ai/paper/2310.07899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07899"}},"official":null}},{"url":"/paper/boosting-continuous-control-with-consistency","slug":"boosting-continuous-control-with-consistency","title":"Boosting Continuous Control with Consistency Policy","date":"2023-10-10","arxiv_id":"2310.06343","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/boosting-continuous-control-with-consistency#ran","syntology_url":"https://syntology.ai/paper/2310.06343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06343"}},"official":{"repos":["cccedric/cpql"],"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/deep-reinforcement-learning-uncovers","slug":"deep-reinforcement-learning-uncovers","title":"Deep reinforcement learning uncovers processes for separating azeotropic mixtures without prior knowledge","date":"2023-10-10","arxiv_id":"2310.06415","repositories_listed":1,"syntology":null},{"url":"/paper/diffcps-diffusion-model-based-constrained","slug":"diffcps-diffusion-model-based-constrained","title":"DiffCPS: Diffusion Model based Constrained Policy Search for Offline Reinforcement Learning","date":"2023-10-09","arxiv_id":"2310.05333","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":4,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/diffcps-diffusion-model-based-constrained#ran","syntology_url":"https://syntology.ai/paper/2310.05333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05333"}},"official":{"repos":["felix-thu/DiffCPS"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-deep-policy-adaptation","slug":"safe-deep-policy-adaptation","title":"Safe Deep Policy Adaptation","date":"2023-10-08","arxiv_id":"2310.08602","repositories_listed":1,"syntology":null},{"url":"/paper/surgical-gym-a-high-performance-gpu-based","slug":"surgical-gym-a-high-performance-gpu-based","title":"Surgical Gym: A high-performance GPU-based platform for reinforcement learning with surgical robots","date":"2023-10-07","arxiv_id":"2310.04676","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-uniform-sampling-offline-reinforcement-1","slug":"beyond-uniform-sampling-offline-reinforcement-1","title":"Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets","date":"2023-10-06","arxiv_id":"2310.04413","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/beyond-uniform-sampling-offline-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2310.04413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04413"}},"official":{"repos":["Improbable-AI/dw-offline-rl"],"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/drift-deep-reinforcement-learning-for-1","slug":"drift-deep-reinforcement-learning-for-1","title":"DRIFT: Deep Reinforcement Learning for Intelligent Floating Platforms Trajectories","date":"2023-10-06","arxiv_id":"2310.04266","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-neuron-segmentation-with","slug":"self-supervised-neuron-segmentation-with","title":"Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning","date":"2023-10-06","arxiv_id":"2310.04148","repositories_listed":1,"syntology":{"n":24,"n_ran":20,"n_constructed":4,"n_ran_checked":18,"n_instrument":2,"n_unverified":4,"n_honours":2,"n_violates":1,"n_no_contract":15,"n_pointer_only":24,"phrase":"20 ran (of which 4 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 1 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/self-supervised-neuron-segmentation-with#ran","syntology_url":"https://syntology.ai/paper/2310.04148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04148"}},"official":{"repos":["ydchen0806/dbmim"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":4,"n_ran_no_instrument_failure":18,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/lesson-learning-to-integrate-exploration","slug":"lesson-learning-to-integrate-exploration","title":"LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework","date":"2023-10-05","arxiv_id":"2310.03342","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":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lesson-learning-to-integrate-exploration#ran","syntology_url":"https://syntology.ai/paper/2310.03342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03342"}},"official":{"repos":["beanie00/lesson"],"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/discovering-general-reinforcement-learning-1","slug":"discovering-general-reinforcement-learning-1","title":"Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design","date":"2023-10-04","arxiv_id":"2310.02782","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/discovering-general-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2310.02782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02782"}},"official":{"repos":["EmptyJackson/groove"],"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/multi-agent-reinforcement-learning-for-power","slug":"multi-agent-reinforcement-learning-for-power","title":"Multi-Agent Reinforcement Learning for Power Grid Topology Optimization","date":"2023-10-04","arxiv_id":"2310.02605","repositories_listed":1,"syntology":null},{"url":"/paper/differentially-encoded-observation-spaces-for","slug":"differentially-encoded-observation-spaces-for","title":"Differentially Encoded Observation Spaces for Perceptive Reinforcement Learning","date":"2023-10-03","arxiv_id":"2310.01767","repositories_listed":1,"syntology":null},{"url":"/paper/prioritized-soft-q-decomposition-for","slug":"prioritized-soft-q-decomposition-for","title":"Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning","date":"2023-10-03","arxiv_id":"2310.02360","repositories_listed":1,"syntology":null},{"url":"/paper/bayesian-design-principles-for-frequentist","slug":"bayesian-design-principles-for-frequentist","title":"Bayesian Design Principles for Frequentist Sequential Learning","date":"2023-10-01","arxiv_id":"2310.00806","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-with-synthetic-data-helps","slug":"pre-training-with-synthetic-data-helps","title":"Pre-training with Synthetic Data Helps Offline Reinforcement Learning","date":"2023-10-01","arxiv_id":"2310.00771","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/pre-training-with-synthetic-data-helps#ran","syntology_url":"https://syntology.ai/paper/2310.00771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00771"}},"official":{"repos":["victor-wang-902/synthetic-pretrain-rl"],"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/combining-spatial-and-temporal-abstraction-in","slug":"combining-spatial-and-temporal-abstraction-in","title":"Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning","date":"2023-09-30","arxiv_id":"2310.00229","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/combining-spatial-and-temporal-abstraction-in#ran","syntology_url":"https://syntology.ai/paper/2310.00229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00229"}},"official":{"repos":["mila-iqia/skipper"],"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":["official"]}}},{"url":"/paper/harmony-world-models-boosting-sample","slug":"harmony-world-models-boosting-sample","title":"HarmonyDream: Task Harmonization Inside World Models","date":"2023-09-30","arxiv_id":"2310.00344","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_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","sample_list":"/paper/harmony-world-models-boosting-sample#ran","syntology_url":"https://syntology.ai/paper/2310.00344","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00344"}},"official":{"repos":["thuml/harmonydream"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cleanba-a-reproducible-and-efficient","slug":"cleanba-a-reproducible-and-efficient","title":"Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform","date":"2023-09-29","arxiv_id":"2310.00036","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"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) · 4 unverified","sample_list":"/paper/cleanba-a-reproducible-and-efficient#ran","syntology_url":"https://syntology.ai/paper/2310.00036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00036"}},"official":{"repos":["vwxyzjn/cleanba"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/estimation-and-inference-in-distributional","slug":"estimation-and-inference-in-distributional","title":"Estimation and Inference in Distributional Reinforcement Learning","date":"2023-09-29","arxiv_id":"2309.17262","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":2,"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: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/estimation-and-inference-in-distributional#ran","syntology_url":"https://syntology.ai/paper/2309.17262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17262"}},"official":{"repos":["zhangliangyu32/estimationandinferencedistributionalrl"],"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/rladapter-bridging-large-language-models-to","slug":"rladapter-bridging-large-language-models-to","title":"AdaRefiner: Refining Decisions of Language Models with Adaptive Feedback","date":"2023-09-29","arxiv_id":"2309.17176","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/rladapter-bridging-large-language-models-to#ran","syntology_url":"https://syntology.ai/paper/2309.17176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17176"}},"official":{"repos":["pku-rl/adarefiner"],"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/towards-robust-offline-to-online","slug":"towards-robust-offline-to-online","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","date":"2023-09-29","arxiv_id":"2309.16973","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-robust-offline-to-online#ran","syntology_url":"https://syntology.ai/paper/2309.16973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16973"}},"official":{"repos":["battlewen/ro2o"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-terminate-in-object-navigation","slug":"learning-to-terminate-in-object-navigation","title":"Learning to Terminate in Object Navigation","date":"2023-09-28","arxiv_id":"2309.16164","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-streaming-video-temporal-action","slug":"end-to-end-streaming-video-temporal-action","title":"End-to-End Streaming Video Temporal Action Segmentation with Reinforce Learning","date":"2023-09-27","arxiv_id":"2309.15683","repositories_listed":1,"syntology":null},{"url":"/paper/towards-human-like-rl-taming-non-naturalistic","slug":"towards-human-like-rl-taming-non-naturalistic","title":"Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Games","date":"2023-09-27","arxiv_id":"2309.15484","repositories_listed":1,"syntology":null},{"url":"/paper/effective-multi-agent-deep-reinforcement","slug":"effective-multi-agent-deep-reinforcement","title":"Effective Multi-Agent Deep Reinforcement Learning Control with Relative Entropy Regularization","date":"2023-09-26","arxiv_id":"2309.14727","repositories_listed":1,"syntology":null},{"url":"/paper/maximum-diffusion-reinforcement-learning","slug":"maximum-diffusion-reinforcement-learning","title":"Maximum diffusion reinforcement learning","date":"2023-09-26","arxiv_id":"2309.15293","repositories_listed":1,"syntology":null},{"url":"/paper/tempo-adaptation-in-non-stationary-1","slug":"tempo-adaptation-in-non-stationary-1","title":"Tempo Adaptation in Non-stationary Reinforcement Learning","date":"2023-09-26","arxiv_id":"2309.14989","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":2,"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/tempo-adaptation-in-non-stationary-1#ran","syntology_url":"https://syntology.ai/paper/2309.14989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.14989"}},"official":{"repos":["hyunin-lee/TempoRL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/designing-and-evaluating-an-online","slug":"designing-and-evaluating-an-online","title":"Designing and evaluating an online reinforcement learning agent for physical exercise recommendations in N-of-1 trials","date":"2023-09-25","arxiv_id":"2309.14156","repositories_listed":1,"syntology":null},{"url":"/paper/guided-cooperation-in-hierarchical","slug":"guided-cooperation-in-hierarchical","title":"Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout","date":"2023-09-24","arxiv_id":"2309.13508","repositories_listed":1,"syntology":null},{"url":"/paper/counterfactual-conservative-q-learning-for-1","slug":"counterfactual-conservative-q-learning-for-1","title":"Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning","date":"2023-09-22","arxiv_id":"2309.12696","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":3,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/counterfactual-conservative-q-learning-for-1#ran","syntology_url":"https://syntology.ai/paper/2309.12696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12696"}},"official":{"repos":["thu-rllab/CFCQL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/omnidrones-an-efficient-and-flexible-platform","slug":"omnidrones-an-efficient-and-flexible-platform","title":"OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control","date":"2023-09-22","arxiv_id":"2309.12825","repositories_listed":1,"syntology":null},{"url":"/paper/sequential-action-induced-invariant","slug":"sequential-action-induced-invariant","title":"Sequential Action-Induced Invariant Representation for Reinforcement Learning","date":"2023-09-22","arxiv_id":"2309.12628","repositories_listed":1,"syntology":null},{"url":"/paper/distributional-pareto-optimal-multi-objective","slug":"distributional-pareto-optimal-multi-objective","title":"Distributional Pareto-Optimal Multi-Objective Reinforcement Learning","date":"2023-09-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/representation-abstractions-as-incentives-for","slug":"representation-abstractions-as-incentives-for","title":"State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping","date":"2023-09-21","arxiv_id":"2309.11984","repositories_listed":1,"syntology":null},{"url":"/paper/text2reward-automated-dense-reward-function","slug":"text2reward-automated-dense-reward-function","title":"Text2Reward: Reward Shaping with Language Models for Reinforcement Learning","date":"2023-09-20","arxiv_id":"2309.11489","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/text2reward-automated-dense-reward-function#ran","syntology_url":"https://syntology.ai/paper/2309.11489","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.11489"}},"official":{"repos":["xlang-ai/text2reward"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/actively-learning-reinforcement-learning-a","slug":"actively-learning-reinforcement-learning-a","title":"Actively Learning Reinforcement Learning: A Stochastic Optimal Control Approach","date":"2023-09-18","arxiv_id":"2309.10831","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-initial-state-buffer-for","slug":"contrastive-initial-state-buffer-for","title":"Contrastive Initial State Buffer for Reinforcement Learning","date":"2023-09-18","arxiv_id":"2309.09752","repositories_listed":1,"syntology":null},{"url":"/paper/projected-task-specific-layers-for-multi-task","slug":"projected-task-specific-layers-for-multi-task","title":"Projected Task-Specific Layers for Multi-Task Reinforcement Learning","date":"2023-09-15","arxiv_id":"2309.08776","repositories_listed":1,"syntology":null},{"url":"/paper/vapor-holonomic-legged-robot-navigation-in","slug":"vapor-holonomic-legged-robot-navigation-in","title":"VAPOR: Legged Robot Navigation in Outdoor Vegetation Using Offline Reinforcement Learning","date":"2023-09-14","arxiv_id":"2309.07832","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-reinforcement-learning-for-jumping","slug":"efficient-reinforcement-learning-for-jumping","title":"Efficient Reinforcement Learning for Jumping Monopods","date":"2023-09-13","arxiv_id":"2309.07038","repositories_listed":1,"syntology":null},{"url":"/paper/a-reinforcement-learning-approach-for-robotic","slug":"a-reinforcement-learning-approach-for-robotic","title":"A Reinforcement Learning Approach for Robotic Unloading from Visual Observations","date":"2023-09-12","arxiv_id":"2309.06621","repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-with-latent-diffusion-in-offline","slug":"reasoning-with-latent-diffusion-in-offline","title":"Reasoning with Latent Diffusion in Offline Reinforcement Learning","date":"2023-09-12","arxiv_id":"2309.06599","repositories_listed":1,"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":6,"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/reasoning-with-latent-diffusion-in-offline#ran","syntology_url":"https://syntology.ai/paper/2309.06599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06599"}},"official":{"repos":["ldcq/ldcq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-for-supply-chain","slug":"reinforcement-learning-for-supply-chain","title":"Reinforcement Learning for Supply Chain Attacks Against Frequency and Voltage Control","date":"2023-09-11","arxiv_id":"2309.05814","repositories_listed":1,"syntology":null},{"url":"/paper/compositional-learning-of-visually-grounded","slug":"compositional-learning-of-visually-grounded","title":"Compositional Learning of Visually-Grounded Concepts Using Reinforcement","date":"2023-09-08","arxiv_id":"2309.04504","repositories_listed":1,"syntology":null},{"url":"/paper/subwords-as-skills-tokenization-for-sparse","slug":"subwords-as-skills-tokenization-for-sparse","title":"Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning","date":"2023-09-08","arxiv_id":"2309.04459","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/subwords-as-skills-tokenization-for-sparse#ran","syntology_url":"https://syntology.ai/paper/2309.04459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.04459"}},"official":{"repos":["dyunis/subwords_as_skills"],"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/learning-of-generalizable-and-interpretable","slug":"learning-of-generalizable-and-interpretable","title":"Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environments","date":"2023-09-07","arxiv_id":"2309.03651","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-from-hierarchical","slug":"deep-reinforcement-learning-from-hierarchical","title":"Deep Reinforcement Learning from Hierarchical Preference Design","date":"2023-09-06","arxiv_id":"2309.02632","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-recharge-uav-coverage-path","slug":"learning-to-recharge-uav-coverage-path","title":"Learning to Recharge: UAV Coverage Path Planning through Deep Reinforcement Learning","date":"2023-09-06","arxiv_id":"2309.03157","repositories_listed":1,"syntology":null},{"url":"/paper/orl-auditor-dataset-auditing-in-offline-deep","slug":"orl-auditor-dataset-auditing-in-offline-deep","title":"ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning","date":"2023-09-06","arxiv_id":"2309.03081","repositories_listed":1,"syntology":null},{"url":"/paper/rlsync-offline-online-reinforcement-learning","slug":"rlsync-offline-online-reinforcement-learning","title":"RLSynC: Offline-Online Reinforcement Learning for Synthon Completion","date":"2023-09-06","arxiv_id":"2309.02671","repositories_listed":1,"syntology":null},{"url":"/paper/autonomous-soft-tissue-retraction-using","slug":"autonomous-soft-tissue-retraction-using","title":"Autonomous Soft Tissue Retraction Using Demonstration-Guided Reinforcement Learning","date":"2023-09-02","arxiv_id":"2309.00837","repositories_listed":1,"syntology":null},{"url":"/paper/let-the-models-respond-interpreting-language","slug":"let-the-models-respond-interpreting-language","title":"Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence","date":"2023-09-01","arxiv_id":"2309.00751","repositories_listed":1,"syntology":null},{"url":"/paper/repo-resilient-model-based-reinforcement","slug":"repo-resilient-model-based-reinforcement","title":"RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability","date":"2023-08-31","arxiv_id":"2309.00082","repositories_listed":1,"syntology":null},{"url":"/paper/the-power-of-meme-adversarial-malware","slug":"the-power-of-meme-adversarial-malware","title":"The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement Learning","date":"2023-08-31","arxiv_id":"2308.16562","repositories_listed":1,"syntology":null},{"url":"/paper/improving-reinforcement-learning-training","slug":"improving-reinforcement-learning-training","title":"Improving Generalization in Reinforcement Learning Training Regimes for Social Robot Navigation","date":"2023-08-29","arxiv_id":"2308.14947","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/improving-reinforcement-learning-training#ran","syntology_url":"https://syntology.ai/paper/2308.14947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14947"}},"official":{"repos":["raise-lab/soc-nav-training"],"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/r-3-on-device-real-time-deep-reinforcement","slug":"r-3-on-device-real-time-deep-reinforcement","title":"R^3: On-device Real-Time Deep Reinforcement Learning for Autonomous Robotics","date":"2023-08-29","arxiv_id":"2308.15039","repositories_listed":1,"syntology":null},{"url":"/paper/context-aware-composition-of-agent-policies","slug":"context-aware-composition-of-agent-policies","title":"Context-Aware Composition of Agent Policies by Markov Decision Process Entity Embeddings and Agent Ensembles","date":"2023-08-28","arxiv_id":"2308.14521","repositories_listed":1,"syntology":null},{"url":"/paper/edge-generation-scheduling-for-dag-tasks","slug":"edge-generation-scheduling-for-dag-tasks","title":"Edge Generation Scheduling for DAG Tasks Using Deep Reinforcement Learning","date":"2023-08-28","arxiv_id":"2308.14647","repositories_listed":1,"syntology":null},{"url":"/paper/learning-visual-tracking-and-reaching-with","slug":"learning-visual-tracking-and-reaching-with","title":"Learning Visual Tracking and Reaching with Deep Reinforcement Learning on a UR10e Robotic Arm","date":"2023-08-28","arxiv_id":"2308.14652","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-for-sampling-on","slug":"reinforcement-learning-for-sampling-on","title":"Reinforcement Learning for Sampling on Temporal Medical Imaging Sequences","date":"2023-08-28","arxiv_id":"2308.14946","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/reinforcement-learning-for-sampling-on#ran","syntology_url":"https://syntology.ai/paper/2308.14946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14946"}},"official":{"repos":["zhishenhuang/rlsamp"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/simple-modification-of-the-upper-confidence","slug":"simple-modification-of-the-upper-confidence","title":"Simple Modification of the Upper Confidence Bound Algorithm by Generalized Weighted Averages","date":"2023-08-28","arxiv_id":"2308.14350","repositories_listed":1,"syntology":null},{"url":"/paper/traffic-light-control-with-reinforcement","slug":"traffic-light-control-with-reinforcement","title":"Traffic Light Control with Reinforcement Learning","date":"2023-08-28","arxiv_id":"2308.14295","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-based-multi-modal","slug":"reinforcement-learning-based-multi-modal","title":"Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class Discovery","date":"2023-08-26","arxiv_id":"2308.13801","repositories_listed":1,"syntology":null},{"url":"/paper/learning-collaborative-information","slug":"learning-collaborative-information","title":"Collaborative Information Dissemination with Graph-based Multi-Agent Reinforcement Learning","date":"2023-08-25","arxiv_id":"2308.16198","repositories_listed":1,"syntology":null},{"url":"/paper/pretty-darn-good-control-when-are-approximate","slug":"pretty-darn-good-control-when-are-approximate","title":"Pretty darn good control: when are approximate solutions better than approximate models","date":"2023-08-25","arxiv_id":"2308.13654","repositories_listed":1,"syntology":null},{"url":"/paper/molopt-autonomous-molecular-geometry","slug":"molopt-autonomous-molecular-geometry","title":"MolOpt: Autonomous Molecular Geometry Optimization using Multi-Agent Reinforcement Learning","date":"2023-08-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-intentional-forgetting-driven-self-healing","slug":"an-intentional-forgetting-driven-self-healing","title":"An Intentional Forgetting-Driven Self-Healing Method For Deep Reinforcement Learning Systems","date":"2023-08-23","arxiv_id":"2308.12445","repositories_listed":1,"syntology":null},{"url":"/paper/deploying-deep-reinforcement-learning-systems","slug":"deploying-deep-reinforcement-learning-systems","title":"Deploying Deep Reinforcement Learning Systems: A Taxonomy of Challenges","date":"2023-08-23","arxiv_id":"2308.12438","repositories_listed":1,"syntology":null},{"url":"/paper/diverse-policies-converge-in-reward-free","slug":"diverse-policies-converge-in-reward-free","title":"Diverse Policies Converge in Reward-free Markov Decision Processe","date":"2023-08-23","arxiv_id":"2308.11924","repositories_listed":1,"syntology":null},{"url":"/paper/language-reward-modulation-for-pretraining","slug":"language-reward-modulation-for-pretraining","title":"Language Reward Modulation for Pretraining Reinforcement Learning","date":"2023-08-23","arxiv_id":"2308.12270","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":1,"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/language-reward-modulation-for-pretraining#ran","syntology_url":"https://syntology.ai/paper/2308.12270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12270"}},"official":{"repos":["ademiadeniji/lamp"],"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/fox-formation-aware-exploration-in-multi","slug":"fox-formation-aware-exploration-in-multi","title":"FoX: Formation-aware exploration in multi-agent reinforcement learning","date":"2023-08-22","arxiv_id":"2308.11272","repositories_listed":1,"syntology":null},{"url":"/paper/lagr-seq-language-guided-reinforcement","slug":"lagr-seq-language-guided-reinforcement","title":"LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying","date":"2023-08-21","arxiv_id":"2308.13542","repositories_listed":1,"syntology":null},{"url":"/paper/dpmac-differentially-private-communication","slug":"dpmac-differentially-private-communication","title":"DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learning","date":"2023-08-19","arxiv_id":"2308.09902","repositories_listed":1,"syntology":null},{"url":"/paper/discrete-prompt-compression-with","slug":"discrete-prompt-compression-with","title":"Discrete Prompt Compression with Reinforcement Learning","date":"2023-08-17","arxiv_id":"2308.08758","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/discrete-prompt-compression-with#ran","syntology_url":"https://syntology.ai/paper/2308.08758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08758"}},"official":{"repos":["nenomigami/promptcompressor"],"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-to-identify-critical-states-for","slug":"learning-to-identify-critical-states-for","title":"Learning to Identify Critical States for Reinforcement Learning from Videos","date":"2023-08-15","arxiv_id":"2308.07795","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"phrase":"9 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-identify-critical-states-for#ran","syntology_url":"https://syntology.ai/paper/2308.07795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07795"}},"official":{"repos":["ai-initiative-kaust/videorlcs"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-in-financial-markets-a","slug":"reinforcement-learning-in-financial-markets-a","title":"Reinforcement Learning in Financial Markets: A Study on Dynamic Model Weight Assignment","date":"2023-08-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/heterogeneous-multi-agent-reinforcement-1","slug":"heterogeneous-multi-agent-reinforcement-1","title":"Heterogeneous Multi-Agent Reinforcement Learning via Mirror Descent Policy Optimization","date":"2023-08-13","arxiv_id":"2308.06741","repositories_listed":1,"syntology":null},{"url":"/paper/value-distributional-model-based","slug":"value-distributional-model-based","title":"Value-Distributional Model-Based Reinforcement Learning","date":"2023-08-12","arxiv_id":"2308.06590","repositories_listed":1,"syntology":null},{"url":"/paper/a-deep-recurrent-reinforcement-learning","slug":"a-deep-recurrent-reinforcement-learning","title":"A Deep Recurrent-Reinforcement Learning Method for Intelligent AutoScaling of Serverless Functions","date":"2023-08-11","arxiv_id":"2308.05937","repositories_listed":1,"syntology":null},{"url":"/paper/rlsac-reinforcement-learning-enhanced-sample","slug":"rlsac-reinforcement-learning-enhanced-sample","title":"RLSAC: Reinforcement Learning enhanced Sample Consensus for End-to-End Robust Estimation","date":"2023-08-10","arxiv_id":"2308.05318","repositories_listed":1,"syntology":null},{"url":"/paper/barlowrl-barlow-twins-for-data-efficient","slug":"barlowrl-barlow-twins-for-data-efficient","title":"BarlowRL: Barlow Twins for Data-Efficient Reinforcement Learning","date":"2023-08-08","arxiv_id":"2308.04263","repositories_listed":1,"syntology":null},{"url":"/paper/alphastar-unplugged-large-scale-offline","slug":"alphastar-unplugged-large-scale-offline","title":"AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning","date":"2023-08-07","arxiv_id":"2308.03526","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"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 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","sample_list":"/paper/alphastar-unplugged-large-scale-offline#ran","syntology_url":"https://syntology.ai/paper/2308.03526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03526"}},"official":null}},{"url":"/paper/minimizing-return-gaps-with-discrete","slug":"minimizing-return-gaps-with-discrete","title":"RGMComm: Return Gap Minimization via Discrete Communications in Multi-Agent Reinforcement Learning","date":"2023-08-07","arxiv_id":"2308.03358","repositories_listed":1,"syntology":null},{"url":"/paper/qdax-a-library-for-quality-diversity-and","slug":"qdax-a-library-for-quality-diversity-and","title":"QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration","date":"2023-08-07","arxiv_id":"2308.03665","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-for-financial-index","slug":"reinforcement-learning-for-financial-index","title":"Reinforcement Learning for Financial Index Tracking","date":"2023-08-05","arxiv_id":"2308.02820","repositories_listed":1,"syntology":null},{"url":"/paper/job-shop-scheduling-via-deep-reinforcement","slug":"job-shop-scheduling-via-deep-reinforcement","title":"Job Shop Scheduling via Deep Reinforcement Learning: a Sequence to Sequence approach","date":"2023-08-03","arxiv_id":"2308.01797","repositories_listed":1,"syntology":null},{"url":"/paper/smarla-a-safety-monitoring-approach-for-deep","slug":"smarla-a-safety-monitoring-approach-for-deep","title":"SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents","date":"2023-08-03","arxiv_id":"2308.02594","repositories_listed":1,"syntology":null},{"url":"/paper/bierl-a-meta-evolutionary-reinforcement","slug":"bierl-a-meta-evolutionary-reinforcement","title":"BiERL: A Meta Evolutionary Reinforcement Learning Framework via Bilevel Optimization","date":"2023-08-01","arxiv_id":"2308.01207","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-based-non","slug":"reinforcement-learning-based-non","title":"Reinforcement Learning-based Non-Autoregressive Solver for Traveling Salesman Problems","date":"2023-08-01","arxiv_id":"2308.00560","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/reinforcement-learning-based-non#ran","syntology_url":"https://syntology.ai/paper/2308.00560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.00560"}},"official":{"repos":["xybfight/nar4tsp"],"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"]}}}],"record_sha256":"79a92ff53db440a36e552b0207bb66799f7ec6987fad68ac99c203749cc6b037","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}