{"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/thompson-sampling/papers/4","list_of":"/task/thompson-sampling","task":"Thompson Sampling","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":4,"pages_in_order":7,"rows_per_page":100,"rows":[301,400],"of":655,"counts":{"archive_papers_tagged":655,"with_a_code_link":135,"where_syntology_ran_a_sample":30,"not_listed_spam_title":0,"listed":655,"listed_where_code_ran":30,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":23,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":23,"listed_every_run_a_failure_of_syntologys_instrument":7,"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/thompson-sampling","prev":"/task/thompson-sampling/papers/3","next":"/task/thompson-sampling/papers/5","papers":[{"url":null,"slug":"a-combinatorial-semi-bandit-approach-to","title":"A Combinatorial Semi-Bandit Approach to Charging Station Selection for Electric Vehicles","date":"2023-01-17","arxiv_id":"2301.07156","repositories_listed":0,"syntology":null},{"url":null,"slug":"thompson-sampling-with-diffusion-generative","title":"Thompson Sampling with Diffusion Generative Prior","date":"2023-01-12","arxiv_id":"2301.05182","repositories_listed":0,"syntology":null},{"url":null,"slug":"ungeneralizable-contextual-logistic-bandit-in","title":"Reinforcement Learning in Credit Scoring and Underwriting","date":"2022-12-15","arxiv_id":"2212.07632","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-learning-based-waveform-selection-for","title":"Online Learning-based Waveform Selection for Improved Vehicle Recognition in Automotive Radar","date":"2022-12-01","arxiv_id":"2212.00615","repositories_listed":0,"syntology":null},{"url":null,"slug":"monte-carlo-tree-search-algorithms-for-risk","title":"Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning","date":"2022-11-23","arxiv_id":"2211.13032","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-learning-of-interface-conditions-for","title":"Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks","date":"2022-10-23","arxiv_id":"2210.12669","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-active-ensemble-sampling-for-image","title":"Deep Active Ensemble Sampling For Image Classification","date":"2022-10-11","arxiv_id":"2210.05770","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-typical-behavior-of-bandit-algorithms","title":"The Typical Behavior of Bandit Algorithms","date":"2022-10-11","arxiv_id":"2210.05660","repositories_listed":0,"syntology":null},{"url":null,"slug":"cost-aware-asynchronous-multi-agent-active","title":"Cost Aware Asynchronous Multi-Agent Active Search","date":"2022-10-05","arxiv_id":"2210.02259","repositories_listed":0,"syntology":null},{"url":null,"slug":"thompson-sampling-with-virtual-helping-agents","title":"Thompson Sampling with Virtual Helping Agents","date":"2022-09-16","arxiv_id":"2209.08197","repositories_listed":0,"syntology":null},{"url":null,"slug":"double-doubly-robust-thompson-sampling-for","title":"Double Doubly Robust Thompson Sampling for Generalized Linear Contextual Bandits","date":"2022-09-15","arxiv_id":"2209.06983","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-nonparametric-contextual-bandit-with-arm","title":"A Nonparametric Contextual Bandit with Arm-level Eligibility Control for Customer Service Routing","date":"2022-09-08","arxiv_id":"2209.05278","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-generative-embeddings-using-an","title":"Sample Efficient Learning of Factored Embeddings of Tensor Fields","date":"2022-09-01","arxiv_id":"2209.00372","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-collaborative-filtering-thompson","title":"Dynamic collaborative filtering Thompson Sampling for cross-domain advertisements recommendation","date":"2022-08-25","arxiv_id":"2208.11926","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-provably-efficient-model-free-posterior-1","title":"A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning","date":"2022-08-23","arxiv_id":"2208.10904","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-stationary-dynamic-pricing-via-actor","title":"Non-Stationary Dynamic Pricing Via Actor-Critic Information-Directed Pricing","date":"2022-08-19","arxiv_id":"2208.09372","repositories_listed":0,"syntology":null},{"url":null,"slug":"increasing-students-engagement-to-reminder","title":"Increasing Students' Engagement to Reminder Emails Through Multi-Armed Bandits","date":"2022-08-10","arxiv_id":"2208.05090","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-adaptive-experiments-to-rapidly-help","title":"Using Adaptive Experiments to Rapidly Help Students","date":"2022-08-10","arxiv_id":"2208.05092","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-optimization-based-beam-alignment","title":"Bayesian Optimization-Based Beam Alignment for MmWave MIMO Communication Systems","date":"2022-07-28","arxiv_id":"2207.14174","repositories_listed":0,"syntology":null},{"url":null,"slug":"sprt-based-efficient-best-arm-identification","title":"SPRT-based Efficient Best Arm Identification in Stochastic Bandits","date":"2022-07-22","arxiv_id":"2207.11158","repositories_listed":0,"syntology":null},{"url":null,"slug":"chimera-a-hybrid-machine-learning-driven","title":"Chimera: A Hybrid Machine Learning Driven Multi-Objective Design Space Exploration Tool for FPGA High-Level Synthesis","date":"2022-07-03","arxiv_id":"2207.07917","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-averse-contextual-multi-armed-bandit","title":"Risk-averse Contextual Multi-armed Bandit Problem with Linear Payoffs","date":"2022-06-24","arxiv_id":"2206.12463","repositories_listed":0,"syntology":null},{"url":null,"slug":"thompson-sampling-efficiently-learns-to","title":"Analysis of Thompson Sampling for Controlling Unknown Linear Diffusion Processes","date":"2022-06-20","arxiv_id":"2206.09977","repositories_listed":0,"syntology":null},{"url":null,"slug":"thompson-sampling-for-combinatorial-pure-1","title":"Thompson Sampling for (Combinatorial) Pure Exploration","date":"2022-06-18","arxiv_id":"2206.09150","repositories_listed":0,"syntology":null},{"url":null,"slug":"thompson-sampling-achieves-tilde-o-sqrt-t","title":"Thompson Sampling Achieves $\\tilde O(\\sqrt{T})$ Regret in Linear Quadratic Control","date":"2022-06-17","arxiv_id":"2206.08520","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-contextual-combinatorial-semi-bandit","title":"A Contextual Combinatorial Semi-Bandit Approach to Network Bottleneck Identification","date":"2022-06-16","arxiv_id":"2206.08144","repositories_listed":0,"syntology":null},{"url":null,"slug":"top-two-algorithms-revisited","title":"Top Two Algorithms Revisited","date":"2022-06-13","arxiv_id":"2206.05979","repositories_listed":0,"syntology":null},{"url":null,"slug":"regret-bounds-for-information-directed","title":"Regret Bounds for Information-Directed Reinforcement Learning","date":"2022-06-09","arxiv_id":"2206.04640","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-and-optimal-policy-design-for-online","title":"A Simple and Optimal Policy Design with Safety against Heavy-Tailed Risk for Stochastic Bandits","date":"2022-06-07","arxiv_id":"2206.02969","repositories_listed":0,"syntology":null},{"url":null,"slug":"finite-time-regret-of-thompson-sampling","title":"Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits","date":"2022-06-07","arxiv_id":"2206.03520","repositories_listed":0,"syntology":null},{"url":null,"slug":"bandit-theory-and-thompson-sampling-guided","title":"Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization","date":"2022-06-05","arxiv_id":"2206.02092","repositories_listed":0,"syntology":null},{"url":null,"slug":"incentivizing-combinatorial-bandit","title":"Incentivizing Combinatorial Bandit Exploration","date":"2022-06-01","arxiv_id":"2206.00494","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifting-the-information-ratio-an-information","title":"Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits","date":"2022-05-27","arxiv_id":"2205.13924","repositories_listed":0,"syntology":null},{"url":null,"slug":"surrogate-modeling-for-bayesian-optimization","title":"Surrogate modeling for Bayesian optimization beyond a single Gaussian process","date":"2022-05-27","arxiv_id":"2205.14090","repositories_listed":0,"syntology":null},{"url":null,"slug":"actively-tracking-the-optimal-arm-in-non","title":"Fast Change Identification in Multi-Play Bandits and its Applications in Wireless Networks","date":"2022-05-20","arxiv_id":"2205.10366","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-parametric-contextual-bandits-with-graph","title":"Semi-Parametric Contextual Bandits with Graph-Laplacian Regularization","date":"2022-05-17","arxiv_id":"2205.08295","repositories_listed":0,"syntology":null},{"url":null,"slug":"adjusted-expected-improvement-for-cumulative","title":"Adjusted Expected Improvement for Cumulative Regret Minimization in Noisy Bayesian Optimization","date":"2022-05-10","arxiv_id":"2205.04901","repositories_listed":0,"syntology":null},{"url":null,"slug":"nonstationary-bandit-learning-via-predictive","title":"Non-Stationary Bandit Learning via Predictive Sampling","date":"2022-05-04","arxiv_id":"2205.01970","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-kernelized-multi-armed-bandits-with","title":"On Kernelized Multi-Armed Bandits with Constraints","date":"2022-03-29","arxiv_id":"2203.15589","repositories_listed":0,"syntology":null},{"url":null,"slug":"thompson-sampling-on-asymmetric-a-stable","title":"Thompson Sampling on Asymmetric $α$-Stable Bandits","date":"2022-03-19","arxiv_id":"2203.10214","repositories_listed":0,"syntology":null},{"url":null,"slug":"regenerative-particle-thompson-sampling","title":"Regenerative Particle Thompson Sampling","date":"2022-03-15","arxiv_id":"2203.08082","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-active-search-using-detection-and","title":"Multi-Agent Active Search using Detection and Location Uncertainty","date":"2022-03-09","arxiv_id":"2203.04524","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-ensemble-sampling","title":"An Analysis of Ensemble Sampling","date":"2022-03-02","arxiv_id":"2203.01303","repositories_listed":0,"syntology":null},{"url":null,"slug":"partial-likelihood-thompson-sampling","title":"Partial Likelihood Thompson Sampling","date":"2022-03-02","arxiv_id":"2203.00820","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-scalable-and-robust-structured","title":"Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework","date":"2022-02-26","arxiv_id":"2202.13227","repositories_listed":0,"syntology":null},{"url":null,"slug":"thompson-sampling-with-unrestricted-delays","title":"Thompson Sampling with Unrestricted Delays","date":"2022-02-24","arxiv_id":"2202.12431","repositories_listed":0,"syntology":null},{"url":null,"slug":"double-thompson-sampling-in-finite-stochastic","title":"Double Thompson Sampling in Finite stochastic Games","date":"2022-02-21","arxiv_id":"2202.10008","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptivity-and-confounding-in-multi-armed","title":"Adaptive Experimentation in the Presence of Exogenous Nonstationary Variation","date":"2022-02-18","arxiv_id":"2202.09036","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-online-inference-for-nonlinear","title":"Fast online inference for nonlinear contextual bandit based on Generative Adversarial Network","date":"2022-02-17","arxiv_id":"2202.08867","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetically-controlled-bandits","title":"Synthetically Controlled Bandits","date":"2022-02-14","arxiv_id":"2202.07079","repositories_listed":0,"syntology":null},{"url":null,"slug":"remote-contextual-bandits","title":"Remote Contextual Bandits","date":"2022-02-10","arxiv_id":"2202.05182","repositories_listed":0,"syntology":null},{"url":null,"slug":"fourier-representations-for-black-box-1","title":"Fourier Representations for Black-Box Optimization over Categorical Variables","date":"2022-02-08","arxiv_id":"2202.03712","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-learning-whittle-index-policy-for-restless","title":"On learning Whittle index policy for restless bandits with scalable regret","date":"2022-02-07","arxiv_id":"2202.03463","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-hierarchy-in-bandits","title":"Deep Hierarchy in Bandits","date":"2022-02-03","arxiv_id":"2202.01454","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmented-rbmle-ucb-approach-for-adaptive","title":"Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems","date":"2022-01-25","arxiv_id":"2201.10542","repositories_listed":0,"syntology":null},{"url":null,"slug":"ibac-an-intelligent-dynamic-bandwidth-channel","title":"IBAC: An Intelligent Dynamic Bandwidth Channel Access Avoiding Outside Warning Range Problem","date":"2022-01-15","arxiv_id":"2201.05727","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-dynamic-pricing-with-covariates","title":"On Dynamic Pricing with Covariates","date":"2021-12-25","arxiv_id":"2112.13254","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithms-for-adaptive-experiments-that","title":"Algorithms for Adaptive Experiments that Trade-off Statistical Analysis with Reward: Combining Uniform Random Assignment and Reward Maximization","date":"2021-12-15","arxiv_id":"2112.08507","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-and-optimal-policies-in-bandit","title":"Risk and optimal policies in bandit experiments","date":"2021-12-13","arxiv_id":"2112.06363","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-linear-leveling-bandits","title":"Safe Linear Leveling Bandits","date":"2021-12-13","arxiv_id":"2112.06728","repositories_listed":0,"syntology":null},{"url":null,"slug":"doubly-robust-thompson-sampling-with-linear","title":"Doubly Robust Thompson Sampling with Linear Payoffs","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"observation-free-attacks-on-stochastic","title":"Observation-Free Attacks on Stochastic Bandits","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-gating-for-single-photon-3d-imaging","title":"Adaptive Gating for Single-Photon 3D Imaging","date":"2021-11-30","arxiv_id":"2111.15047","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-bayesian-bandits","title":"Hierarchical Bayesian Bandits","date":"2021-11-12","arxiv_id":"2111.06929","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-hardness-analysis-of-thompson-sampling","title":"The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle","date":"2021-11-08","arxiv_id":"2111.04295","repositories_listed":0,"syntology":null},{"url":null,"slug":"maillard-sampling-boltzmann-exploration-done","title":"Maillard Sampling: Boltzmann Exploration Done Optimally","date":"2021-11-05","arxiv_id":"2111.03290","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-learning-of-energy-consumption-for","title":"Online Learning of Energy Consumption for Navigation of Electric Vehicles","date":"2021-11-03","arxiv_id":"2111.02314","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-inference-without-trading-off","title":"Efficient Inference Without Trading-off Regret in Bandits: An Allocation Probability Test for Thompson Sampling","date":"2021-10-30","arxiv_id":"2111.00137","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-bayesian-optimistic-sampling","title":"Variational Bayesian Optimistic Sampling","date":"2021-10-29","arxiv_id":"2110.15688","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentially-private-federated-bayesian","title":"Differentially Private Federated Bayesian Optimization with Distributed Exploration","date":"2021-10-27","arxiv_id":"2110.14153","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-thompson-sampling-for-partially","title":"Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Bandits","date":"2021-10-23","arxiv_id":"2110.12175","repositories_listed":0,"syntology":null},{"url":null,"slug":"diversified-sampling-for-batched-bayesian","title":"Diversified Sampling for Batched Bayesian Optimization with Determinantal Point Processes","date":"2021-10-22","arxiv_id":"2110.11665","repositories_listed":0,"syntology":null},{"url":null,"slug":"feel-good-thompson-sampling-for-contextual","title":"Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning","date":"2021-10-02","arxiv_id":"2110.00871","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymptotic-performance-of-thompson-sampling","title":"Asymptotic Performance of Thompson Sampling in the Batched Multi-Armed Bandits","date":"2021-10-01","arxiv_id":"2110.00158","repositories_listed":0,"syntology":null},{"url":null,"slug":"batched-thompson-sampling","title":"Batched Thompson Sampling","date":"2021-10-01","arxiv_id":"2110.00202","repositories_listed":0,"syntology":null},{"url":null,"slug":"apple-tasting-revisited-bayesian-approaches","title":"Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classification","date":"2021-09-29","arxiv_id":"2109.14412","repositories_listed":0,"syntology":null},{"url":null,"slug":"expected-improvement-based-contextual-bandits","title":"Expected Improvement-based Contextual Bandits","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"regularized-ofu-an-efficient-algorithm-for","title":"Regularized-OFU: an efficient algorithm for general contextual bandit with optimization oracles","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-exploration-for-recommendation-systems","title":"Deep Exploration for Recommendation Systems","date":"2021-09-26","arxiv_id":"2109.12509","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-learning-of-network-bottlenecks-via","title":"Online Learning of Network Bottlenecks via Minimax Paths","date":"2021-09-17","arxiv_id":"2109.08467","repositories_listed":0,"syntology":null},{"url":null,"slug":"thompson-sampling-for-bandits-with-clustered","title":"Thompson Sampling for Bandits with Clustered Arms","date":"2021-09-06","arxiv_id":"2109.01656","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-relaxed-technical-assumption-for-posterior","title":"A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems","date":"2021-08-19","arxiv_id":"2108.08502","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-regret-for-learning-to-control","title":"Scalable regret for learning to control network-coupled subsystems with unknown dynamics","date":"2021-08-18","arxiv_id":"2108.07970","repositories_listed":0,"syntology":null},{"url":null,"slug":"batched-thompson-sampling-for-multi-armed","title":"Batched Thompson Sampling for Multi-Armed Bandits","date":"2021-08-15","arxiv_id":"2108.06812","repositories_listed":0,"syntology":null},{"url":null,"slug":"metadata-based-multi-task-bandits-with","title":"Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models","date":"2021-08-13","arxiv_id":"2108.06422","repositories_listed":0,"syntology":null},{"url":null,"slug":"debiasing-samples-from-online-learning-using","title":"Debiasing Samples from Online Learning Using Bootstrap","date":"2021-07-31","arxiv_id":"2108.00236","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptively-optimize-content-recommendation","title":"Adaptively Optimize Content Recommendation Using Multi Armed Bandit Algorithms in E-commerce","date":"2021-07-30","arxiv_id":"2108.01440","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-probabilistic-inference-in-deep","title":"From Predictions to Decisions: The Importance of Joint Predictive Distributions","date":"2021-07-20","arxiv_id":"2107.09224","repositories_listed":0,"syntology":null},{"url":null,"slug":"guideboot-guided-bootstrap-for-deep","title":"GuideBoot: Guided Bootstrap for Deep Contextual Bandits","date":"2021-07-18","arxiv_id":"2107.08383","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-regrets-for-learning-the-prior-in-bandits","title":"No Regrets for Learning the Prior in Bandits","date":"2021-07-13","arxiv_id":"2107.06196","repositories_listed":0,"syntology":null},{"url":null,"slug":"metalearning-linear-bandits-by-prior-update","title":"Metalearning Linear Bandits by Prior Update","date":"2021-07-12","arxiv_id":"2107.05320","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-decision-making-under-misspecified","title":"Bayesian decision-making under misspecified priors with applications to meta-learning","date":"2021-07-03","arxiv_id":"2107.01509","repositories_listed":0,"syntology":null},{"url":null,"slug":"markov-decision-process-modeled-with-bandits","title":"Markov Decision Process modeled with Bandits for Sequential Decision Making in Linear-flow","date":"2021-07-01","arxiv_id":"2107.00204","repositories_listed":0,"syntology":null},{"url":null,"slug":"random-effect-bandits","title":"Random Effect Bandits","date":"2021-06-23","arxiv_id":"2106.12200","repositories_listed":0,"syntology":null},{"url":null,"slug":"thompson-sampling-for-unimodal-bandits","title":"Thompson Sampling for Unimodal Bandits","date":"2021-06-15","arxiv_id":"2106.08187","repositories_listed":0,"syntology":null},{"url":null,"slug":"thompson-sampling-with-a-mixture-prior","title":"Thompson Sampling with a Mixture Prior","date":"2021-06-10","arxiv_id":"2106.05608","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandit-algorithms-on-system-on","title":"Multi-armed Bandit Algorithms on System-on-Chip: Go Frequentist or Bayesian?","date":"2021-06-05","arxiv_id":"2106.02855","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-closer-look-at-the-worst-case-behavior-of","title":"A Closer Look at the Worst-case Behavior of Multi-armed Bandit Algorithms","date":"2021-06-03","arxiv_id":"2106.02126","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallelizing-thompson-sampling","title":"Parallelizing Thompson Sampling","date":"2021-06-02","arxiv_id":"2106.01420","repositories_listed":0,"syntology":null},{"url":null,"slug":"kolmogorov-smirnov-test-based-actively","title":"Kolmogorov-Smirnov Test-Based Actively-Adaptive Thompson Sampling for Non-Stationary Bandits","date":"2021-05-30","arxiv_id":"2105.14586","repositories_listed":0,"syntology":null}],"record_sha256":"4092a2415749bb13167ee6094935cb306501df9750258624e45dbf08253e709f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}