{"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/multi-armed-bandits/papers/7","list_of":"/task/multi-armed-bandits","task":"Multi-Armed Bandits","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":7,"pages_in_order":13,"rows_per_page":100,"rows":[601,700],"of":1262,"counts":{"archive_papers_tagged":1262,"with_a_code_link":253,"where_syntology_ran_a_sample":55,"not_listed_spam_title":0,"listed":1262,"listed_where_code_ran":55,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":44,"every_run_a_failure_of_syntologys_instrument":11,"listed_with_a_run_with_no_instrument_failure":44,"listed_every_run_a_failure_of_syntologys_instrument":11,"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/multi-armed-bandits","prev":"/task/multi-armed-bandits/papers/6","next":"/task/multi-armed-bandits/papers/8","papers":[{"url":null,"slug":"leveraging-user-triggered-supervision-in","title":"Leveraging User-Triggered Supervision in Contextual Bandits","date":"2023-02-07","arxiv_id":"2302.03784","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-private-and-robust-bandits","title":"On Private and Robust Bandits","date":"2023-02-06","arxiv_id":"2302.02526","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiplier-bootstrap-based-exploration","title":"Multiplier Bootstrap-based Exploration","date":"2023-02-03","arxiv_id":"2302.01543","repositories_listed":0,"syntology":null},{"url":null,"slug":"randomized-greedy-learning-for-non-monotone","title":"Randomized Greedy Learning for Non-monotone Stochastic Submodular Maximization Under Full-bandit Feedback","date":"2023-02-02","arxiv_id":"2302.01324","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-contextual-bandits-with-long","title":"Stochastic Contextual Bandits with Long Horizon Rewards","date":"2023-02-02","arxiv_id":"2302.00814","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-algorithms-for-multi-period-multi","title":"Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback","date":"2023-01-31","arxiv_id":"2301.13791","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-contextual-bandits-and-recommender","title":"Quantum contextual bandits and recommender systems for quantum data","date":"2023-01-31","arxiv_id":"2301.13524","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-adapting-offline-algorithms","title":"A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit Feedback","date":"2023-01-30","arxiv_id":"2301.13326","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attacks-on-adversarial-bandits","title":"Adversarial Attacks on Adversarial Bandits","date":"2023-01-30","arxiv_id":"2301.12595","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-causal-bayesian-optimisation","title":"Contextual Causal Bayesian Optimisation","date":"2023-01-29","arxiv_id":"2301.12412","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-regret-minimization-in-multi","title":"Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits","date":"2023-01-26","arxiv_id":"2301.11442","repositories_listed":0,"syntology":null},{"url":null,"slug":"banker-online-mirror-descent-a-universal","title":"Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning","date":"2023-01-25","arxiv_id":"2301.10500","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-heavy-tailed-bandits","title":"Quantum Heavy-tailed Bandits","date":"2023-01-23","arxiv_id":"2301.09680","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-and-quantum-channel","title":"Multi-Armed Bandits and Quantum Channel Oracles","date":"2023-01-20","arxiv_id":"2301.08544","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandit-learning-for-tdma","title":"Multi-armed Bandit Learning for TDMA Transmission Slot Scheduling and Defragmentation for Improved Bandwidth Usage","date":"2023-01-14","arxiv_id":"2302.05301","repositories_listed":0,"syntology":null},{"url":null,"slug":"best-arm-identification-in-stochastic-bandits","title":"Best Arm Identification in Stochastic Bandits: Beyond $β-$optimality","date":"2023-01-10","arxiv_id":"2301.03785","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-differential-privacy-for-sequential","title":"Local Differential Privacy for Sequential Decision Making in a Changing Environment","date":"2023-01-02","arxiv_id":"2301.00561","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandits-and-optimistically","title":"Contextual Bandits and Optimistically Universal Learning","date":"2022-12-31","arxiv_id":"2301.00241","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-statistical-inference-for-contextual","title":"Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descent","date":"2022-12-30","arxiv_id":"2212.14883","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-complexity-of-representation-learning","title":"On the Complexity of Representation Learning in Contextual Linear Bandits","date":"2022-12-19","arxiv_id":"2212.09429","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-maximum-inner-product-search-in-high","title":"Faster Maximum Inner Product Search in High Dimensions","date":"2022-12-14","arxiv_id":"2212.07551","repositories_listed":0,"syntology":null},{"url":null,"slug":"corruption-robust-algorithms-with-uncertainty","title":"Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes","date":"2022-12-12","arxiv_id":"2212.05949","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-regret-optimal-cooperative-nonstochastic","title":"On Regret-optimal Cooperative Nonstochastic Multi-armed Bandits","date":"2022-11-30","arxiv_id":"2211.17154","repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-pure-exploration-multi-armed","title":"Constrained Pure Exploration Multi-Armed Bandits with a Fixed Budget","date":"2022-11-27","arxiv_id":"2211.14768","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-re-solving-heuristic-for-binary","title":"Contextual Decision-Making with Knapsacks Beyond the Worst Case","date":"2022-11-25","arxiv_id":"2211.13952","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandits-in-a-survey-experiment-on","title":"Contextual Bandits in a Survey Experiment on Charitable Giving: Within-Experiment Outcomes versus Policy Learning","date":"2022-11-22","arxiv_id":"2211.12004","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-for-contextual-multi-armed","title":"Transfer Learning for Contextual Multi-armed Bandits","date":"2022-11-22","arxiv_id":"2211.12612","repositories_listed":0,"syntology":null},{"url":null,"slug":"bandit-algorithms-for-prophet-inequality-and","title":"Bandit Algorithms for Prophet Inequality and Pandora's Box","date":"2022-11-16","arxiv_id":"2211.08586","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-bandits-online-decision-making-in","title":"Causal Bandits: Online Decision-Making in Endogenous Settings","date":"2022-11-16","arxiv_id":"2211.08649","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-player-bandits-robust-to-adversarial","title":"Multi-Player Bandits Robust to Adversarial Collisions","date":"2022-11-15","arxiv_id":"2211.07817","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-penalization-in-stochastic-multi-armed","title":"On Penalization in Stochastic Multi-armed Bandits","date":"2022-11-15","arxiv_id":"2211.08311","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-contextual-bandits-with-knapsacks","title":"Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression","date":"2022-11-14","arxiv_id":"2211.07484","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypothesis-transfer-in-bandits-by-weighted","title":"Hypothesis Transfer in Bandits by Weighted Models","date":"2022-11-14","arxiv_id":"2211.07387","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizing-distribution-of-partial-rewards","title":"Generalizing distribution of partial rewards for multi-armed bandits with temporally-partitioned rewards","date":"2022-11-13","arxiv_id":"2211.06883","repositories_listed":0,"syntology":null},{"url":null,"slug":"contexts-can-be-cheap-solving-stochastic","title":"Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithms","date":"2022-11-08","arxiv_id":"2211.05632","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-simple-regret-minimization-in","title":"Revisiting Simple Regret: Fast Rates for Returning a Good Arm","date":"2022-10-30","arxiv_id":"2210.16913","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-contextual-linear-bandits","title":"Robust Contextual Linear Bandits","date":"2022-10-26","arxiv_id":"2210.14483","repositories_listed":0,"syntology":null},{"url":null,"slug":"pac-bayesian-offline-contextual-bandits-with","title":"PAC-Bayesian Offline Contextual Bandits With Guarantees","date":"2022-10-24","arxiv_id":"2210.13132","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-representation-learning-in-linear","title":"Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees","date":"2022-10-24","arxiv_id":"2210.13083","repositories_listed":0,"syntology":null},{"url":null,"slug":"vertical-federated-linear-contextual-bandits","title":"Vertical Federated Linear Contextual Bandits","date":"2022-10-20","arxiv_id":"2210.11050","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandits-with-concave-rewards-and","title":"Contextual bandits with concave rewards, and an application to fair ranking","date":"2022-10-18","arxiv_id":"2210.09957","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-entropy-exploration-in-contextual","title":"Maximum entropy exploration in contextual bandits with neural networks and energy based models","date":"2022-10-12","arxiv_id":"2210.06302","repositories_listed":0,"syntology":null},{"url":null,"slug":"constant-regret-for-sequence-prediction-with","title":"Constant regret for sequence prediction with limited advice","date":"2022-10-05","arxiv_id":"2210.02256","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-prototype-selection-via-multi-armed","title":"ProtoBandit: Efficient Prototype Selection via Multi-Armed Bandits","date":"2022-10-04","arxiv_id":"2210.01860","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-high-probability-regret-for","title":"Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs","date":"2022-10-04","arxiv_id":"2210.01376","repositories_listed":0,"syntology":null},{"url":null,"slug":"reproducible-bandits","title":"Replicable Bandits","date":"2022-10-04","arxiv_id":"2210.01898","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-best-arm-identification-with-a-fixed","title":"On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits","date":"2022-09-30","arxiv_id":"2210.00895","repositories_listed":0,"syntology":null},{"url":null,"slug":"off-policy-risk-assessment-in-markov-decision","title":"Off-Policy Risk Assessment in Markov Decision Processes","date":"2022-09-21","arxiv_id":"2209.10444","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-inference-for-autonomous-decision","title":"Active Inference for Autonomous Decision-Making with Contextual Multi-Armed Bandits","date":"2022-09-19","arxiv_id":"2209.09185","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-off-policy-evaluation-via","title":"Towards Robust Off-Policy Evaluation via Human Inputs","date":"2022-09-18","arxiv_id":"2209.08682","repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-policy-optimization-for","title":"Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems","date":"2022-09-17","arxiv_id":"2209.08429","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":"risk-aware-linear-bandits-with-convex-loss","title":"Risk-aware linear bandits with convex loss","date":"2022-09-15","arxiv_id":"2209.07154","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-averse-multi-armed-bandits-with","title":"Risk-Averse Multi-Armed Bandits with Unobserved Confounders: A Case Study in Emotion Regulation in Mobile Health","date":"2022-09-09","arxiv_id":"2209.04356","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-with-self-information","title":"Multi-Armed Bandits with Self-Information Rewards","date":"2022-09-06","arxiv_id":"2209.02211","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-privacy-meets-partial-information-a","title":"When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits","date":"2022-09-06","arxiv_id":"2209.02570","repositories_listed":0,"syntology":null},{"url":null,"slug":"exposure-aware-recommendation-using","title":"Exposure-Aware Recommendation using Contextual Bandits","date":"2022-09-04","arxiv_id":"2209.01665","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-inference-for-model-free-and","title":"Variational Inference for Model-Free and Model-Based Reinforcement Learning","date":"2022-09-04","arxiv_id":"2209.01693","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-global-sensitivity-for-differentially","title":"Dynamic Global Sensitivity for Differentially Private Contextual Bandits","date":"2022-08-30","arxiv_id":"2208.14555","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":"understanding-the-stochastic-dynamics-of","title":"Understanding the stochastic dynamics of sequential decision-making processes: A path-integral analysis of multi-armed bandits","date":"2022-08-11","arxiv_id":"2208.06245","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":"raising-student-completion-rates-with","title":"Raising Student Completion Rates with Adaptive Curriculum and Contextual Bandits","date":"2022-07-28","arxiv_id":"2207.14003","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-soft-fairness-in-restless-multi-armed","title":"Towards Soft Fairness in Restless Multi-Armed Bandits","date":"2022-07-27","arxiv_id":"2207.13343","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":"online-learning-with-off-policy-feedback","title":"Online Learning with Off-Policy Feedback","date":"2022-07-18","arxiv_id":"2207.08956","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-best-arm-identification-with","title":"Parallel Best Arm Identification in Heterogeneous Environments","date":"2022-07-16","arxiv_id":"2207.08015","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-selection-in-reinforcement-learning","title":"Model Selection in Reinforcement Learning with General Function Approximations","date":"2022-07-06","arxiv_id":"2207.02992","repositories_listed":0,"syntology":null},{"url":null,"slug":"instance-optimal-pac-algorithms-for","title":"Instance-optimal PAC Algorithms for Contextual Bandits","date":"2022-07-05","arxiv_id":"2207.02357","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-drug-design-with-multi-armed","title":"Autonomous Drug Design with Multi-Armed Bandits","date":"2022-07-04","arxiv_id":"2207.01393","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-representation-training-in-sequential","title":"Joint Representation Training in Sequential Tasks with Shared Structure","date":"2022-06-24","arxiv_id":"2206.12441","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiple-play-stochastic-bandits-with","title":"Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms","date":"2022-06-17","arxiv_id":"2206.08776","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":"pure-exploration-of-causal-bandits","title":"Combinatorial Pure Exploration of Causal Bandits","date":"2022-06-16","arxiv_id":"2206.07883","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-differential-privacy-in-multi","title":"Distributed Differential Privacy in Multi-Armed Bandits","date":"2022-06-12","arxiv_id":"2206.05772","repositories_listed":0,"syntology":null},{"url":null,"slug":"squeeze-all-novel-estimator-and-self","title":"Squeeze All: Novel Estimator and Self-Normalized Bound for Linear Contextual Bandits","date":"2022-06-11","arxiv_id":"2206.05404","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-efficient-distributed-learning-3","title":"Communication Efficient Distributed Learning for Kernelized Contextual Bandits","date":"2022-06-10","arxiv_id":"2206.04835","repositories_listed":0,"syntology":null},{"url":null,"slug":"conformal-off-policy-prediction-in-contextual","title":"Conformal Off-Policy Prediction in Contextual Bandits","date":"2022-06-09","arxiv_id":"2206.04405","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-resource-allocation-with-fairness","title":"Efficient Resource Allocation with Fairness Constraints in Restless Multi-Armed Bandits","date":"2022-06-08","arxiv_id":"2206.03883","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-bandit-with-arm-group-graph","title":"Neural Bandit with Arm Group Graph","date":"2022-06-08","arxiv_id":"2206.03644","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":"asymptotic-instance-optimal-algorithms-for","title":"Asymptotic Instance-Optimal Algorithms for Interactive Decision Making","date":"2022-06-06","arxiv_id":"2206.02326","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-pareto-set-identification-with","title":"Robust Pareto Set Identification with Contaminated Bandit Feedback","date":"2022-06-06","arxiv_id":"2206.02666","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandits-with-knapsacks-for-a","title":"Contextual Bandits with Knapsacks for a Conversion Model","date":"2022-06-01","arxiv_id":"2206.00314","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-meta-learning-in-adversarial-multi","title":"Online Meta-Learning in Adversarial Multi-Armed Bandits","date":"2022-05-31","arxiv_id":"2205.15921","repositories_listed":0,"syntology":null},{"url":null,"slug":"provable-general-function-class","title":"Provable General Function Class Representation Learning in Multitask Bandits and MDPs","date":"2022-05-31","arxiv_id":"2205.15701","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-and-practically-efficient-neural","title":"Provably and Practically Efficient Neural Contextual Bandits","date":"2022-05-31","arxiv_id":"2206.00099","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-multi-armed-bandits-and-stochastic","title":"Quantum Multi-Armed Bandits and Stochastic Linear Bandits Enjoy Logarithmic Regrets","date":"2022-05-30","arxiv_id":"2205.14988","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairness-and-welfare-quantification-for","title":"Fairness and Welfare Quantification for Regret in Multi-Armed Bandits","date":"2022-05-27","arxiv_id":"2205.13930","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":"meta-learning-adversarial-bandits","title":"Meta-Learning Adversarial Bandits","date":"2022-05-27","arxiv_id":"2205.14128","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-pandora-s-box","title":"Contextual Pandora's Box","date":"2022-05-26","arxiv_id":"2205.13114","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-exploitation-and-engagement-in","title":"Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment","date":"2022-05-26","arxiv_id":"2205.13566","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-contextual-bandits-based-dynamic","title":"Neural Contextual Bandits Based Dynamic Sensor Selection for Low-Power Body-Area Networks","date":"2022-05-24","arxiv_id":"2205.11832","repositories_listed":0,"syntology":null},{"url":null,"slug":"computationally-efficient-horizon-free","title":"Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs","date":"2022-05-23","arxiv_id":"2205.11507","repositories_listed":0,"syntology":null},{"url":null,"slug":"falsification-of-multiple-requirements-for","title":"Falsification of Multiple Requirements for Cyber-Physical Systems Using Online Generative Adversarial Networks and Multi-Armed Bandits","date":"2022-05-23","arxiv_id":"2205.11057","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-information-directed-sampling","title":"Contextual Information-Directed Sampling","date":"2022-05-22","arxiv_id":"2205.10895","repositories_listed":0,"syntology":null},{"url":null,"slug":"pessimism-for-offline-linear-contextual","title":"Pessimism for Offline Linear Contextual Bandits using $\\ell_p$ Confidence Sets","date":"2022-05-21","arxiv_id":"2205.10671","repositories_listed":0,"syntology":null},{"url":null,"slug":"stability-enforced-bandit-algorithms-for","title":"Stability Enforced Bandit Algorithms for Channel Selection in Remote State Estimation of Gauss-Markov Processes","date":"2022-05-20","arxiv_id":"2205.09923","repositories_listed":0,"syntology":null}],"record_sha256":"064309c9d2662afdd9f6d294c5da03635805b264bcda24decf7d73bdc85ee502","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}