{"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/12","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":12,"pages_in_order":13,"rows_per_page":100,"rows":[1101,1200],"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/11","next":"/task/multi-armed-bandits/papers/13","papers":[{"url":null,"slug":"fighting-contextual-bandits-with-stochastic","title":"Fighting Contextual Bandits with Stochastic Smoothing","date":"2018-10-11","arxiv_id":"1810.05188","repositories_listed":0,"syntology":null},{"url":null,"slug":"regularized-contextual-bandits","title":"Regularized Contextual Bandits","date":"2018-10-11","arxiv_id":"1810.05065","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-multi-armed-bandits-for-causal","title":"Contextual Multi-Armed Bandits for Causal Marketing","date":"2018-10-02","arxiv_id":"1810.01859","repositories_listed":0,"syntology":null},{"url":null,"slug":"thompson-sampling-for-cascading-bandits","title":"Thompson Sampling Algorithms for Cascading Bandits","date":"2018-10-02","arxiv_id":"1810.01187","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandits-with-cross-learning","title":"Contextual Bandits with Cross-learning","date":"2018-09-25","arxiv_id":"1809.09582","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-player-bandits-a-trekking-approach","title":"Multi-Player Bandits: A Trekking Approach","date":"2018-09-17","arxiv_id":"1809.06040","repositories_listed":0,"syntology":null},{"url":null,"slug":"diversity-driven-selection-of-exploration","title":"Diversity-Driven Selection of Exploration Strategies in Multi-Armed Bandits","date":"2018-08-23","arxiv_id":"1808.07739","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-poisoning-attacks-in-contextual-bandits","title":"Data Poisoning Attacks in Contextual Bandits","date":"2018-08-17","arxiv_id":"1808.05760","repositories_listed":0,"syntology":null},{"url":null,"slug":"preference-based-online-learning-with-dueling","title":"Preference-based Online Learning with Dueling Bandits: A Survey","date":"2018-07-30","arxiv_id":"1807.11398","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-contextual-multi-armed-bandits","title":"Deep Contextual Multi-armed Bandits","date":"2018-07-25","arxiv_id":"1807.09809","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-optimal-algorithm-for-stochastic-and","title":"Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits","date":"2018-07-19","arxiv_id":"1807.07623","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandits-under-delayed-feedback","title":"Linear Bandits with Stochastic Delayed Feedback","date":"2018-07-05","arxiv_id":"1807.02089","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-user-multi-armed-bandits-for","title":"Multi-User Multi-Armed Bandits for Uncoordinated Spectrum Access","date":"2018-07-02","arxiv_id":"1807.00867","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-coordinate-with-coordination","title":"Learning to Coordinate with Coordination Graphs in Repeated Single-Stage Multi-Agent Decision Problems","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandits-with-surrogate-losses","title":"Contextual bandits with surrogate losses: Margin bounds and efficient algorithms","date":"2018-06-28","arxiv_id":"1806.10745","repositories_listed":0,"syntology":null},{"url":null,"slug":"greybox-fuzzing-as-a-contextual-bandits","title":"Greybox fuzzing as a contextual bandits problem","date":"2018-06-11","arxiv_id":"1806.03806","repositories_listed":0,"syntology":null},{"url":null,"slug":"finding-the-bandit-in-a-graph-sequential","title":"Finding the bandit in a graph: Sequential search-and-stop","date":"2018-06-06","arxiv_id":"1806.02282","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-bias-in-adaptive-data-gathering","title":"Mitigating Bias in Adaptive Data Gathering via Differential Privacy","date":"2018-06-06","arxiv_id":"1806.02329","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-general-approach-to-multi-armed-bandits","title":"A General Framework for Bandit Problems Beyond Cumulative Objectives","date":"2018-06-04","arxiv_id":"1806.01380","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-externalities-of-exploration-and-how-data","title":"The Externalities of Exploration and How Data Diversity Helps Exploitation","date":"2018-06-01","arxiv_id":"1806.00543","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-statistic-approximate-bayesian","title":"Multi-Statistic Approximate Bayesian Computation with Multi-Armed Bandits","date":"2018-05-22","arxiv_id":"1805.08647","repositories_listed":0,"syntology":null},{"url":null,"slug":"pg-ts-improved-thompson-sampling-for-logistic","title":"PG-TS: Improved Thompson Sampling for Logistic Contextual Bandits","date":"2018-05-18","arxiv_id":"1805.07458","repositories_listed":0,"syntology":null},{"url":null,"slug":"delegating-via-quitting-games","title":"Delegating via Quitting Games","date":"2018-04-20","arxiv_id":"1804.07464","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-difficulty-ranking-with-multi-armed","title":"Combining Difficulty Ranking with Multi-Armed Bandits to Sequence Educational Content","date":"2018-04-14","arxiv_id":"1804.05212","repositories_listed":0,"syntology":null},{"url":null,"slug":"best-arm-identification-in-multi-armed","title":"Best arm identification in multi-armed bandits with delayed feedback","date":"2018-03-29","arxiv_id":"1803.10937","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-doubling-tricks-can-and-cant-do-for","title":"What Doubling Tricks Can and Can't Do for Multi-Armed Bandits","date":"2018-03-19","arxiv_id":"1803.06971","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-for-correlated-markovian","title":"Multi-Armed Bandits for Correlated Markovian Environments with Smoothed Reward Feedback","date":"2018-03-11","arxiv_id":"1803.04008","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-learning-over-a-finite-action-set-with","title":"Online learning over a finite action set with limited switching","date":"2018-03-05","arxiv_id":"1803.01548","repositories_listed":0,"syntology":null},{"url":null,"slug":"practical-contextual-bandits-with-regression","title":"Practical Contextual Bandits with Regression Oracles","date":"2018-03-03","arxiv_id":"1803.01088","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-k-nearest-neighbour-ucb-algorithm-for","title":"The K-Nearest Neighbour UCB algorithm for multi-armed bandits with covariates","date":"2018-03-01","arxiv_id":"1803.00316","repositories_listed":0,"syntology":null},{"url":null,"slug":"regional-multi-armed-bandits","title":"Regional Multi-Armed Bandits","date":"2018-02-22","arxiv_id":"1802.07917","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-learning-with-an-unknown-fairness","title":"Online Learning with an Unknown Fairness Metric","date":"2018-02-20","arxiv_id":"1802.06936","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-on-partially-revealed","title":"Multi-Armed Bandits on Partially Revealed Unit Interval Graphs","date":"2018-02-12","arxiv_id":"1802.04339","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-gradients-for-contextual","title":"Policy Gradients for Contextual Recommendations","date":"2018-02-12","arxiv_id":"1802.04162","repositories_listed":0,"syntology":null},{"url":null,"slug":"make-the-minority-great-again-first-order","title":"Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits","date":"2018-02-09","arxiv_id":"1802.03386","repositories_listed":0,"syntology":null},{"url":null,"slug":"nonparametric-stochastic-contextual-bandits","title":"Nonparametric Stochastic Contextual Bandits","date":"2018-01-05","arxiv_id":"1801.01750","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-memory-bandit-for-pro-active","title":"Contextual memory bandit for pro-active dialog engagement","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"active-search-for-high-recall-a-non","title":"Active Search for High Recall: a Non-Stationary Extension of Thompson Sampling","date":"2017-12-27","arxiv_id":"1712.09550","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-multi-armed-bandits-in-constant","title":"Stochastic Multi-armed Bandits in Constant Space","date":"2017-12-25","arxiv_id":"1712.09007","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaussian-process-bandits-with-adaptive","title":"Gaussian Process bandits with adaptive discretization","date":"2017-12-05","arxiv_id":"1712.01447","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-kl-lucb-algorithm-for-large-scale","title":"A KL-LUCB algorithm for Large-Scale Crowdsourcing","date":"2017-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"online-learning-via-differential-privacy","title":"Online Learning via the Differential Privacy Lens","date":"2017-11-27","arxiv_id":"1711.10019","repositories_listed":0,"syntology":null},{"url":null,"slug":"customized-nonlinear-bandits-for-online","title":"Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models","date":"2017-11-22","arxiv_id":"1711.08493","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimation-considerations-in-contextual","title":"Estimation Considerations in Contextual Bandits","date":"2017-11-19","arxiv_id":"1711.07077","repositories_listed":0,"syntology":null},{"url":null,"slug":"budget-constrained-multi-armed-bandits-with","title":"Budget-Constrained Multi-Armed Bandits with Multiple Plays","date":"2017-11-16","arxiv_id":"1711.05928","repositories_listed":0,"syntology":null},{"url":null,"slug":"skyline-identification-in-multi-armed-bandits","title":"Skyline Identification in Multi-Armed Bandits","date":"2017-11-12","arxiv_id":"1711.04213","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-loss-bounds-for-online-learning-with","title":"Small-loss bounds for online learning with partial information","date":"2017-11-09","arxiv_id":"1711.03639","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-player-bandits-revisited","title":"Multi-Player Bandits Revisited","date":"2017-11-07","arxiv_id":"1711.02317","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparsity-variance-and-curvature-in-multi","title":"Sparsity, variance and curvature in multi-armed bandits","date":"2017-11-03","arxiv_id":"1711.01037","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-with-metric-movement","title":"Multi-Armed Bandits with Metric Movement Costs","date":"2017-10-24","arxiv_id":"1710.08997","repositories_listed":0,"syntology":null},{"url":null,"slug":"combinatorial-multi-armed-bandits-for-real","title":"Combinatorial Multi-armed Bandits for Real-Time Strategy Games","date":"2017-10-13","arxiv_id":"1710.04805","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-the-value-of-information-when","title":"An Analysis of the Value of Information when Exploring Stochastic, Discrete Multi-Armed Bandits","date":"2017-10-08","arxiv_id":"1710.02869","repositories_listed":0,"syntology":null},{"url":null,"slug":"trend-detection-based-regret-minimization-for","title":"Trend Detection based Regret Minimization for Bandit Problems","date":"2017-09-15","arxiv_id":"1709.05156","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-learning-for-sequential-decision","title":"Optimal Learning for Sequential Decision Making for Expensive Cost Functions with Stochastic Binary Feedbacks","date":"2017-09-13","arxiv_id":"1709.05216","repositories_listed":0,"syntology":null},{"url":null,"slug":"easeml-towards-multi-tenant-resource-sharing","title":"Ease.ml: Towards Multi-tenant Resource Sharing for Machine Learning Workloads","date":"2017-08-24","arxiv_id":"1708.07308","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-contextual-bandits-in-non","title":"Efficient Contextual Bandits in Non-stationary Worlds","date":"2017-08-05","arxiv_id":"1708.01799","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-techniques-for-outer","title":"Reinforcement learning techniques for Outer Loop Link Adaptation in 4G/5G systems","date":"2017-08-03","arxiv_id":"1708.00994","repositories_listed":0,"syntology":null},{"url":null,"slug":"safety-aware-algorithms-for-adversarial","title":"Safety-Aware Algorithms for Adversarial Contextual Bandit","date":"2017-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-learning-in-multiagent","title":"A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity","date":"2017-07-28","arxiv_id":"1707.09183","repositories_listed":0,"syntology":null},{"url":null,"slug":"nonlinear-sequential-accepts-and-rejects-for","title":"Nonlinear Sequential Accepts and Rejects for Identification of Top Arms in Stochastic Bandits","date":"2017-07-09","arxiv_id":"1707.02649","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-reinforcement-learning-via-initial","title":"Efficient Reinforcement Learning via Initial Pure Exploration","date":"2017-06-07","arxiv_id":"1706.02237","repositories_listed":0,"syntology":null},{"url":null,"slug":"nearly-optimal-sampling-algorithms-for","title":"Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration","date":"2017-06-04","arxiv_id":"1706.01081","repositories_listed":0,"syntology":null},{"url":null,"slug":"boltzmann-exploration-done-right","title":"Boltzmann Exploration Done Right","date":"2017-05-29","arxiv_id":"1705.10257","repositories_listed":0,"syntology":null},{"url":null,"slug":"combinatorial-multi-armed-bandits-with","title":"Combinatorial Multi-Armed Bandits with Filtered Feedback","date":"2017-05-26","arxiv_id":"1705.09605","repositories_listed":0,"syntology":null},{"url":null,"slug":"boundary-crossing-probabilities-for-general","title":"Boundary Crossing Probabilities for General Exponential Families","date":"2017-05-24","arxiv_id":"1705.08814","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-learning-for-contextual-bandits","title":"Multi-Task Learning for Contextual Bandits","date":"2017-05-24","arxiv_id":"1705.08618","repositories_listed":0,"syntology":null},{"url":null,"slug":"combinatorial-semi-bandits-with-knapsacks","title":"Combinatorial Semi-Bandits with Knapsacks","date":"2017-05-23","arxiv_id":"1705.08110","repositories_listed":0,"syntology":null},{"url":null,"slug":"practical-algorithms-for-best-k","title":"Practical Algorithms for Best-K Identification in Multi-Armed Bandits","date":"2017-05-19","arxiv_id":"1705.06894","repositories_listed":0,"syntology":null},{"url":null,"slug":"bandit-regret-scaling-with-the-effective-loss","title":"Bandit Regret Scaling with the Effective Loss Range","date":"2017-05-15","arxiv_id":"1705.05091","repositories_listed":0,"syntology":null},{"url":null,"slug":"value-directed-exploration-in-multi-armed","title":"Value Directed Exploration in Multi-Armed Bandits with Structured Priors","date":"2017-04-12","arxiv_id":"1704.03926","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-kernelized-multi-armed-bandits","title":"On Kernelized Multi-armed Bandits","date":"2017-04-03","arxiv_id":"1704.00445","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-benchmarking-of-nlp-apis-using","title":"Efficient Benchmarking of NLP APIs using Multi-armed Bandits","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"selective-harvesting-over-networks","title":"Selective Harvesting over Networks","date":"2017-03-15","arxiv_id":"1703.05082","repositories_listed":0,"syntology":null},{"url":null,"slug":"horde-of-bandits-using-gaussian-markov-random","title":"Horde of Bandits using Gaussian Markov Random Fields","date":"2017-03-07","arxiv_id":"1703.02626","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-optimal-algorithms-for-generalized","title":"Provably Optimal Algorithms for Generalized Linear Contextual Bandits","date":"2017-02-28","arxiv_id":"1703.00048","repositories_listed":0,"syntology":null},{"url":null,"slug":"qos-aware-multi-armed-bandits","title":"QoS-Aware Multi-Armed Bandits","date":"2017-02-28","arxiv_id":"1703.10669","repositories_listed":0,"syntology":null},{"url":null,"slug":"rotting-bandits","title":"Rotting Bandits","date":"2017-02-23","arxiv_id":"1702.07274","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-the-hazard-rate-more-perturbation","title":"Beyond the Hazard Rate: More Perturbation Algorithms for Adversarial Multi-armed Bandits","date":"2017-02-17","arxiv_id":"1702.05536","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-use-learners-advice","title":"Learning to Use Learners' Advice","date":"2017-02-16","arxiv_id":"1702.04825","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-price-of-differential-privacy-for-online","title":"The Price of Differential Privacy For Online Learning","date":"2017-01-27","arxiv_id":"1701.07953","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-search-for-sparse-signals-with-region","title":"Active Search for Sparse Signals with Region Sensing","date":"2016-12-02","arxiv_id":"1612.00583","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-competing-with-optimal","title":"Multi-armed Bandits: Competing with Optimal Sequences","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weighted-bandits-or-how-bandits-learn","title":"Bandit algorithms to emulate human decision making using probabilistic distortions","date":"2016-11-30","arxiv_id":"1611.10283","repositories_listed":0,"syntology":null},{"url":null,"slug":"fair-algorithms-for-infinite-and-contextual","title":"Fair Algorithms for Infinite and Contextual Bandits","date":"2016-10-29","arxiv_id":"1610.09559","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-aware-algorithms-for-adversarial","title":"Risk-Aware Algorithms for Adversarial Contextual Bandits","date":"2016-10-17","arxiv_id":"1610.05129","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-potential","title":"Exploration Potential","date":"2016-09-16","arxiv_id":"1609.04994","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-sequential-elimination-algorithms-for-best","title":"On Sequential Elimination Algorithms for Best-Arm Identification in Multi-Armed Bandits","date":"2016-09-08","arxiv_id":"1609.02606","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-identification-and-mitigation-of","title":"On the Identification and Mitigation of Weaknesses in the Knowledge Gradient Policy for Multi-Armed Bandits","date":"2016-07-20","arxiv_id":"1607.05970","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-optimal-learning-method-for-developing","title":"An optimal learning method for developing personalized treatment regimes","date":"2016-07-06","arxiv_id":"1607.01462","repositories_listed":0,"syntology":null},{"url":null,"slug":"making-contextual-decisions-with-low","title":"Making Contextual Decisions with Low Technical Debt","date":"2016-06-13","arxiv_id":"1606.03966","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandits-with-latent-confounders-an","title":"Contextual Bandits with Latent Confounders: An NMF Approach","date":"2016-06-01","arxiv_id":"1606.00119","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-regret-bounds-for-oracle-based","title":"Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits","date":"2016-06-01","arxiv_id":"1606.00313","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-problem-best-arm-identification-almost","title":"Open Problem: Best Arm Identification: Almost Instance-Wise Optimality and the Gap Entropy Conjecture","date":"2016-05-27","arxiv_id":"1605.08481","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairness-in-learning-classic-and-contextual","title":"Fairness in Learning: Classic and Contextual Bandits","date":"2016-05-23","arxiv_id":"1605.07139","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-clustering-bandits-for-recommendation","title":"Graph Clustering Bandits for Recommendation","date":"2016-05-02","arxiv_id":"1605.00596","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-contextual-bandits-with-known","title":"Stochastic Contextual Bandits with Known Reward Functions","date":"2016-04-30","arxiv_id":"1605.00176","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-contextual-bandits-and-their","title":"Latent Contextual Bandits and their Application to Personalized Recommendations for New Users","date":"2016-04-22","arxiv_id":"1604.06743","repositories_listed":0,"syntology":null},{"url":null,"slug":"pac-reinforcement-learning-with-rich","title":"PAC Reinforcement Learning with Rich Observations","date":"2016-02-08","arxiv_id":"1602.02722","repositories_listed":0,"syntology":null},{"url":null,"slug":"bistro-an-efficient-relaxation-based-method","title":"BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits","date":"2016-02-06","arxiv_id":"1602.02196","repositories_listed":0,"syntology":null},{"url":null,"slug":"bandits-meet-computer-architecture-designing","title":"Bandits meet Computer Architecture: Designing a Smartly-allocated Cache","date":"2016-01-31","arxiv_id":"1602.00309","repositories_listed":0,"syntology":null}],"record_sha256":"3553246e8a725742d20d3ede42c237021e35bdeb83db3f188bb6e8b0f365007d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}