{"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/10","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":10,"pages_in_order":13,"rows_per_page":100,"rows":[901,1000],"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/9","next":"/task/multi-armed-bandits/papers/11","papers":[{"url":null,"slug":"optimal-algorithms-for-stochastic-multi-armed","title":"Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards","date":"2020-10-24","arxiv_id":"2010.12866","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-algorithm-for-unsupervised-sequential","title":"Online Algorithm for Unsupervised Sequential Selection with Contextual Information","date":"2020-10-23","arxiv_id":"2010.12353","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-semi-supervised-learning-with-bandit","title":"Online Semi-Supervised Learning with Bandit Feedback","date":"2020-10-23","arxiv_id":"2010.12574","repositories_listed":0,"syntology":null},{"url":null,"slug":"achieving-user-side-fairness-in-contextual","title":"Achieving User-Side Fairness in Contextual Bandits","date":"2020-10-22","arxiv_id":"2010.12102","repositories_listed":0,"syntology":null},{"url":null,"slug":"dba-bandits-self-driving-index-tuning-under","title":"DBA bandits: Self-driving index tuning under ad-hoc, analytical workloads with safety guarantees","date":"2020-10-19","arxiv_id":"2010.09208","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-bandits-with-vector-losses","title":"Stochastic Bandits with Vector Losses: Minimizing $\\ell^\\infty$-Norm of Relative Losses","date":"2020-10-15","arxiv_id":"2010.08061","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymptotic-randomised-control-with","title":"Asymptotic Randomised Control with applications to bandits","date":"2020-10-14","arxiv_id":"2010.07252","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-with-dependent-arms","title":"Multi-Armed Bandits with Dependent Arms","date":"2020-10-13","arxiv_id":"2010.09478","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-to-delays-and-data-in-adversarial","title":"Adapting to Delays and Data in Adversarial Multi-Armed Bandits","date":"2020-10-12","arxiv_id":"2010.06022","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-and-distribution-free-robustness","title":"Online and Distribution-Free Robustness: Regression and Contextual Bandits with Huber Contamination","date":"2020-10-08","arxiv_id":"2010.04157","repositories_listed":0,"syntology":null},{"url":null,"slug":"instance-dependent-complexity-of-contextual","title":"Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective","date":"2020-10-07","arxiv_id":"2010.03104","repositories_listed":0,"syntology":null},{"url":null,"slug":"corrattack-black-box-adversarial-attack-with-1","title":"CorrAttack: Black-box Adversarial Attack with Structured Search","date":"2020-10-03","arxiv_id":"2010.01250","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-reinforcement-learning-more-difficult-than","title":"Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon","date":"2020-09-28","arxiv_id":"2009.13503","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandits-for-adapting-to-changing","title":"Contextual Bandits for adapting to changing User preferences over time","date":"2020-09-21","arxiv_id":"2009.10073","repositories_listed":0,"syntology":null},{"url":null,"slug":"regret-bounds-and-reinforcement-learning","title":"Regret Bounds and Reinforcement Learning Exploration of EXP-based Algorithms","date":"2020-09-20","arxiv_id":"2009.09538","repositories_listed":0,"syntology":null},{"url":null,"slug":"partial-bandit-and-semi-bandit-making-the","title":"Partial Bandit and Semi-Bandit: Making the Most Out of Scarce Users' Feedback","date":"2020-09-16","arxiv_id":"2009.07518","repositories_listed":0,"syntology":null},{"url":null,"slug":"thompson-sampling-for-unsupervised-sequential","title":"Thompson Sampling for Unsupervised Sequential Selection","date":"2020-09-16","arxiv_id":"2009.07554","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-based-fast","title":"Deep Contextual Bandits for Fast Initial Access in mmWave Based User-Centric Ultra-Dense Networks","date":"2020-09-15","arxiv_id":"2009.06974","repositories_listed":0,"syntology":null},{"url":null,"slug":"unifying-clustered-and-non-stationary-bandits","title":"Unifying Clustered and Non-stationary Bandits","date":"2020-09-05","arxiv_id":"2009.02463","repositories_listed":0,"syntology":null},{"url":null,"slug":"statistically-robust-risk-averse-best-arm","title":"Statistically Robust, Risk-Averse Best Arm Identification in Multi-Armed Bandits","date":"2020-08-28","arxiv_id":"2008.13629","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-batch-learning-in-high-dimensional","title":"Dynamic Batch Learning in High-Dimensional Sparse Linear Contextual Bandits","date":"2020-08-27","arxiv_id":"2008.11918","repositories_listed":0,"syntology":null},{"url":"/paper/a-sleeping-recovering-bandit-algorithm-for","slug":"a-sleeping-recovering-bandit-algorithm-for","title":"A Sleeping, Recovering Bandit Algorithm for Optimizing Recurring Notifications","date":"2020-08-23","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandits-for-advertising-budget","title":"Contextual Bandits for Advertising Budget Allocation","date":"2020-08-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-contextual-multi-armed-bandits-for","title":"Offline Contextual Multi-armed Bandits for Mobile Health Interventions: A Case Study on Emotion Regulation","date":"2020-08-21","arxiv_id":"2008.09472","repositories_listed":0,"syntology":null},{"url":null,"slug":"kernel-methods-for-cooperative-multi-agent","title":"Kernel Methods for Cooperative Multi-Agent Contextual Bandits","date":"2020-08-14","arxiv_id":"2008.06220","repositories_listed":0,"syntology":null},{"url":null,"slug":"lenient-regret-for-multi-armed-bandits","title":"Lenient Regret for Multi-Armed Bandits","date":"2020-08-10","arxiv_id":"2008.03959","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-optimizing-covid-19-testing","title":"A framework for optimizing COVID-19 testing policy using a Multi Armed Bandit approach","date":"2020-07-28","arxiv_id":"2007.14805","repositories_listed":0,"syntology":null},{"url":null,"slug":"greedy-bandits-with-sampled-context","title":"Greedy Bandits with Sampled Context","date":"2020-07-27","arxiv_id":"2007.16001","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-for-minesweeper-profiting","title":"Multi-Armed Bandits for Minesweeper: Profiting from Exploration-Exploitation Synergy","date":"2020-07-25","arxiv_id":"2007.12824","repositories_listed":0,"syntology":null},{"url":null,"slug":"competing-bandits-the-perils-of-exploration-1","title":"Competing Bandits: The Perils of Exploration Under Competition","date":"2020-07-20","arxiv_id":"2007.10144","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimax-policy-for-heavy-tailed-multi-armed","title":"Minimax Policy for Heavy-tailed Bandits","date":"2020-07-20","arxiv_id":"2007.10493","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-tuning-bandits-over-unknown-covariate","title":"Self-Tuning Bandits over Unknown Covariate-Shifts","date":"2020-07-16","arxiv_id":"2007.08584","repositories_listed":0,"syntology":null},{"url":null,"slug":"upper-counterfactual-confidence-bounds-a-new","title":"Upper Counterfactual Confidence Bounds: a New Optimism Principle for Contextual Bandits","date":"2020-07-15","arxiv_id":"2007.07876","repositories_listed":0,"syntology":null},{"url":null,"slug":"fair-algorithms-for-multi-agent-multi-armed","title":"Fair Algorithms for Multi-Agent Multi-Armed Bandits","date":"2020-07-13","arxiv_id":"2007.06699","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-multi-agent-multi-armed-bandits","title":"Robust Multi-Agent Multi-Armed Bandits","date":"2020-07-07","arxiv_id":"2007.03812","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-with-local-differential","title":"Multi-Armed Bandits with Local Differential Privacy","date":"2020-07-06","arxiv_id":"2007.03121","repositories_listed":0,"syntology":null},{"url":null,"slug":"linear-bandits-with-limited-adaptivity-and","title":"Linear Bandits with Limited Adaptivity and Learning Distributional Optimal Design","date":"2020-07-04","arxiv_id":"2007.01980","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-time-multi-armed-bandits-with","title":"Continuous-Time Multi-Armed Bandits with Controlled Restarts","date":"2020-06-30","arxiv_id":"2007.00081","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-learning-with-corrupted-context","title":"Online learning with Corrupted context: Corrupted Contextual Bandits","date":"2020-06-26","arxiv_id":"2006.15194","repositories_listed":0,"syntology":null},{"url":null,"slug":"approximating-a-target-distribution-using","title":"Approximating a Target Distribution using Weight Queries","date":"2020-06-24","arxiv_id":"2006.13636","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-discretization-for-adversarial","title":"Adaptive Discretization against an Adversary: Lipschitz bandits, Dynamic Pricing, and Auction Tuning","date":"2020-06-22","arxiv_id":"2006.12367","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-optimism-in-model-based-reinforcement","title":"Towards Tractable Optimism in Model-Based Reinforcement Learning","date":"2020-06-21","arxiv_id":"2006.11911","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-problem-model-selection-for-contextual","title":"Open Problem: Model Selection for Contextual Bandits","date":"2020-06-19","arxiv_id":"2006.10940","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-by-repetition-stochastic-multi-armed","title":"Learning by Repetition: Stochastic Multi-armed Bandits under Priming Effect","date":"2020-06-18","arxiv_id":"2006.10356","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-bandits-with-linear-constraints","title":"Stochastic Bandits with Linear Constraints","date":"2020-06-17","arxiv_id":"2006.10185","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-network-utility-maximization-with","title":"Stochastic Network Utility Maximization with Unknown Utilities: Multi-Armed Bandits Approach","date":"2020-06-17","arxiv_id":"2006.09997","repositories_listed":0,"syntology":null},{"url":null,"slug":"piecewise-stationary-off-policy-optimization","title":"Non-Stationary Off-Policy Optimization","date":"2020-06-15","arxiv_id":"2006.08236","repositories_listed":0,"syntology":null},{"url":null,"slug":"explicit-best-arm-identification-in-linear","title":"Explicit Best Arm Identification in Linear Bandits Using No-Regret Learners","date":"2020-06-13","arxiv_id":"2006.07562","repositories_listed":0,"syntology":null},{"url":null,"slug":"bandits-with-partially-observable-offline","title":"Bandits with Partially Observable Confounded Data","date":"2020-06-11","arxiv_id":"2006.06731","repositories_listed":0,"syntology":null},{"url":null,"slug":"best-arm-identification-for-quantile-bandits","title":"Quantile Multi-Armed Bandits: Optimal Best-Arm Identification and a Differentially Private Scheme","date":"2020-06-11","arxiv_id":"2006.06792","repositories_listed":0,"syntology":null},{"url":null,"slug":"ts-ucb-improving-on-thompson-sampling-with","title":"TS-UCB: Improving on Thompson Sampling With Little to No Additional Computation","date":"2020-06-11","arxiv_id":"2006.06372","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributional-robust-batch-contextual","title":"Distributionally Robust Batch Contextual Bandits","date":"2020-06-10","arxiv_id":"2006.05630","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneously-learning-stochastic-and","title":"Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition","date":"2020-06-10","arxiv_id":"2006.05606","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentiable-meta-learning-in-contextual","title":"Meta-Learning Bandit Policies by Gradient Ascent","date":"2020-06-09","arxiv_id":"2006.05094","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandits-with-side-observations","title":"Contextual Bandits with Side-Observations","date":"2020-06-06","arxiv_id":"2006.03951","repositories_listed":0,"syntology":null},{"url":null,"slug":"concurrent-decentralized-channel-allocation","title":"Concurrent Decentralized Channel Allocation and Access Point Selection using Multi-Armed Bandits in multi BSS WLANs","date":"2020-06-05","arxiv_id":"2006.03350","repositories_listed":0,"syntology":null},{"url":null,"slug":"locally-differentially-private-combinatorial","title":"(Locally) Differentially Private Combinatorial Semi-Bandits","date":"2020-06-01","arxiv_id":"2006.00706","repositories_listed":0,"syntology":null},{"url":null,"slug":"to-update-or-not-to-update-delayed","title":"To update or not to update? Delayed Nonparametric Bandits with Randomized Allocation","date":"2020-05-26","arxiv_id":"2005.13078","repositories_listed":0,"syntology":null},{"url":null,"slug":"greedy-algorithm-almost-dominates-in-smoothed","title":"Greedy Algorithm almost Dominates in Smoothed Contextual Bandits","date":"2020-05-19","arxiv_id":"2005.10624","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-retraining-for-model-serving","title":"Neural Network Retraining for Model Serving","date":"2020-04-29","arxiv_id":"2004.14203","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-rank-in-the-position-based-model","title":"Learning to Rank in the Position Based Model with Bandit Feedback","date":"2020-04-27","arxiv_id":"2004.13106","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-batch-learning-in-finite-action","title":"Sequential Batch Learning in Finite-Action Linear Contextual Bandits","date":"2020-04-14","arxiv_id":"2004.06321","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-with-limited-memory-streaming","title":"Exploration with Limited Memory: Streaming Algorithms for Coin Tossing, Noisy Comparisons, and Multi-Armed Bandits","date":"2020-04-09","arxiv_id":"2004.04666","repositories_listed":0,"syntology":null},{"url":null,"slug":"hawkes-process-multi-armed-bandits-for","title":"Hawkes Process Multi-armed Bandits for Disaster Search and Rescue","date":"2020-04-03","arxiv_id":"2004.01580","repositories_listed":0,"syntology":null},{"url":null,"slug":"bypassing-the-monster-a-faster-and-simpler","title":"Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits under Realizability","date":"2020-03-28","arxiv_id":"2003.12699","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-no-regret-learning-in-repeated-first","title":"Optimal No-regret Learning in Repeated First-price Auctions","date":"2020-03-22","arxiv_id":"2003.09795","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-contextual-bandits-in","title":"Self-Supervised Contextual Bandits in Computer Vision","date":"2020-03-18","arxiv_id":"2003.08485","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-and-fairness-in-energy-harvesting-a","title":"Learning and Fairness in Energy Harvesting: A Maximin Multi-Armed Bandits Approach","date":"2020-03-13","arxiv_id":"2003.06213","repositories_listed":0,"syntology":null},{"url":null,"slug":"delay-adaptive-learning-in-generalized-linear","title":"Delay-Adaptive Learning in Generalized Linear Contextual Bandits","date":"2020-03-11","arxiv_id":"2003.05174","repositories_listed":0,"syntology":null},{"url":null,"slug":"convex-hull-monte-carlo-tree-search","title":"Convex Hull Monte-Carlo Tree Search","date":"2020-03-09","arxiv_id":"2003.04445","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-residential-demand-response-via","title":"Online Residential Demand Response via Contextual Multi-Armed Bandits","date":"2020-03-07","arxiv_id":"2003.03627","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-farewell-to-arms-sequential-reward","title":"A Farewell to Arms: Sequential Reward Maximization on a Budget with a Giving Up Option","date":"2020-03-06","arxiv_id":"2003.03456","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-policy-elimination-an-efficient","title":"Generalized Policy Elimination: an efficient algorithm for Nonparametric Contextual Bandits","date":"2020-03-05","arxiv_id":"2003.02873","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustness-guarantees-for-mode-estimation","title":"Robustness Guarantees for Mode Estimation with an Application to Bandits","date":"2020-03-05","arxiv_id":"2003.02932","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-linear-contextual-bandits-with","title":"Stochastic Linear Contextual Bandits with Diverse Contexts","date":"2020-03-05","arxiv_id":"2003.02681","repositories_listed":0,"syntology":null},{"url":null,"slug":"taking-a-hint-how-to-leverage-loss-predictors","title":"Taking a hint: How to leverage loss predictors in contextual bandits?","date":"2020-03-04","arxiv_id":"2003.01922","repositories_listed":0,"syntology":null},{"url":null,"slug":"bounded-regret-for-finitely-parameterized","title":"Bounded Regret for Finitely Parameterized Multi-Armed Bandits","date":"2020-03-03","arxiv_id":"2003.01328","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-cooperative-decision-making-in-1","title":"Distributed Cooperative Decision Making in Multi-agent Multi-armed Bandits","date":"2020-03-03","arxiv_id":"2003.01312","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-selection-in-contextual-stochastic","title":"Model Selection in Contextual Stochastic Bandit Problems","date":"2020-03-03","arxiv_id":"2003.01704","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-multi-player-multi-armed","title":"Decentralized Multi-player Multi-armed Bandits with No Collision Information","date":"2020-02-29","arxiv_id":"2003.00162","repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-truthful-contextual-multi-armed","title":"Designing Truthful Contextual Multi-Armed Bandits based Sponsored Search Auctions","date":"2020-02-26","arxiv_id":"2002.11349","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-linear-contextual-bandits-a-sharp","title":"Structured Linear Contextual Bandits: A Sharp and Geometric Smoothed Analysis","date":"2020-02-26","arxiv_id":"2002.11332","repositories_listed":0,"syntology":null},{"url":null,"slug":"fair-bandit-learning-with-delayed-impact-of","title":"Bandit Learning with Delayed Impact of Actions","date":"2020-02-24","arxiv_id":"2002.10316","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-bandits-with-regret-guarantees","title":"Survey Bandits with Regret Guarantees","date":"2020-02-23","arxiv_id":"2002.09814","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-learning-in-contextual-bandits-using","title":"Online Learning in Contextual Bandits using Gated Linear Networks","date":"2020-02-21","arxiv_id":"2002.11611","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-conditional-versus-marginal-bias-in-multi","title":"On conditional versus marginal bias in multi-armed bandits","date":"2020-02-19","arxiv_id":"2002.08422","repositories_listed":0,"syntology":null},{"url":null,"slug":"residual-bootstrap-exploration-for-bandit","title":"Residual Bootstrap Exploration for Bandit Algorithms","date":"2020-02-19","arxiv_id":"2002.08436","repositories_listed":0,"syntology":null},{"url":null,"slug":"coordination-without-communication-optimal","title":"Coordination without communication: optimal regret in two players multi-armed bandits","date":"2020-02-14","arxiv_id":"2002.07596","repositories_listed":0,"syntology":null},{"url":null,"slug":"tight-lower-bounds-for-combinatorial-multi","title":"Tight Lower Bounds for Combinatorial Multi-Armed Bandits","date":"2020-02-13","arxiv_id":"2002.05392","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-general-framework-to-analyze-stochastic","title":"A General Theory of the Stochastic Linear Bandit and Its Applications","date":"2020-02-12","arxiv_id":"2002.05152","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-ucb-optimal-and-efficient-contextual","title":"Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles","date":"2020-02-12","arxiv_id":"2002.04926","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attacks-on-linear-contextual","title":"Adversarial Attacks on Linear Contextual Bandits","date":"2020-02-10","arxiv_id":"2002.03839","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-for-batched-bandits","title":"Inference for Batched Bandits","date":"2020-02-08","arxiv_id":"2002.03217","repositories_listed":0,"syntology":null},{"url":null,"slug":"selfish-robustness-and-equilibria-in-multi","title":"Selfish Robustness and Equilibria in Multi-Player Bandits","date":"2020-02-04","arxiv_id":"2002.01197","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-complexity-of-incentivized-exploration","title":"The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexity","date":"2020-02-03","arxiv_id":"2002.00558","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-closer-look-at-small-loss-bounds-for","title":"A Closer Look at Small-loss Bounds for Bandits with Graph Feedback","date":"2020-02-02","arxiv_id":"2002.00315","repositories_listed":0,"syntology":null},{"url":null,"slug":"advances-in-bandits-with-knapsacks","title":"Bandits with Knapsacks beyond the Worst-Case","date":"2020-02-01","arxiv_id":"2002.00253","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-and-robust-algorithms-for","title":"Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits","date":"2020-02-01","arxiv_id":"2002.00287","repositories_listed":0,"syntology":null},{"url":null,"slug":"ballooning-multi-armed-bandits","title":"Ballooning Multi-Armed Bandits","date":"2020-01-24","arxiv_id":"2001.10055","repositories_listed":0,"syntology":null},{"url":null,"slug":"incentivising-exploration-and-recommendations","title":"Incentivising Exploration and Recommendations for Contextual Bandits with Payments","date":"2020-01-22","arxiv_id":"2001.07853","repositories_listed":0,"syntology":null}],"record_sha256":"5937eb9c041f1b8baacbe25fada0e086f6269f223bcf02ed34de24ecee36982b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}