An information-theoretic analysis of Thompson sampling
From MaRDI portal
Recommendations
- Thompson sampling: an asymptotically optimal finite-time analysis
- Near-optimal regret bounds for Thompson sampling
- A Tutorial on Thompson Sampling
- On the Prior Sensitivity of Thompson Sampling
- Thompson Sampling for Stochastic Control: The Finite Parameter Case
- scientific article; zbMATH DE number 7626733
- Linear Thompson sampling revisited
- Thompson Sampling for Stochastic Control: The Continuous Parameter Case
- Thompson Sampling for Bayesian Bandits with Resets
- An information-theoretic analysis of return maximization in reinforcement learning
Cited in
(47)- Generalizations of maximal inequalities to arbitrary selection rules
- Foraging decisions as multi-armed bandit problems: applying reinforcement learning algorithms to foraging data
- Exploratory distributions for convex functions
- Improved regret for zeroth-order adversarial bandit convex optimisation
- Dismemberment and design for controlling the replication variance of regret for the multi-armed bandit
- Probabilistic bisection with spatial metamodels
- Adaptive policies for perimeter surveillance problems
- An information-theoretic analysis of return maximization in reinforcement learning
- On the Prior Sensitivity of Thompson Sampling
- Thompson sampling: an asymptotically optimal finite-time analysis
- A survey on online learning methods: Thompson sampling and others
- A Tutorial on Thompson Sampling
- Near-optimal regret bounds for Thompson sampling
- Multi-armed bandit for species discovery: a Bayesian nonparametric approach
- Learning to optimize via information-directed sampling
- Matching while learning
- Bandit Theory: Applications to Learning Healthcare Systems and Clinical Trials
- Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning
- Nonstationary bandits with habituation and recovery dynamics
- Efficient Simulation of High Dimensional Gaussian Vectors
- Derivative-free optimization methods
- Learning to optimize via posterior sampling
- On the Worth of Perfect Information in Bandits with Random Discounting
- Satisficing in Time-Sensitive Bandit Learning
- Entropy Regularization for Mean Field Games with Learning
- A Bayesian approach to (online) transfer learning: theory and algorithms
- Information theory for ranking and selection
- Reward Maximization Through Discrete Active Inference
- Reinforcement Learning, Bit by Bit
- Nearly Dimension-Independent Sparse Linear Bandit over Small Action Spaces via Best Subset Selection
- Lower bounds on the noiseless worst-case complexity of efficient global optimization
- Thompson sampling for networked control over unknown channels
- Generalized probabilistic bisection for stochastic root finding
- Occupancy information ratio: infinite-horizon, information-directed, parameterized policy search
- Hiring as exploration
- Sequential Monte Carlo bandits
- Bayesian design principles for frequentist sequential learning
- Thompson sampling for zero-inflated count outcomes with an application to the drink less mobile health study
- Simple fixes that accommodate switching costs in multi-armed bandits
- Output-weighted sampling for multi-armed bandits with extreme payoffs
- Stochastic Low-Rank Tensor Bandits for Multi-Dimensional Online Decision Making
- Unified algorithms for RL with decision-estimation coefficients: PAC, reward-free, preference-based learning and beyond
- Feedback graph regret bounds for Thompson sampling and UCB
- Thompson sampling for adversarial bit prediction
- First-order Bayesian regret analysis of Thompson sampling
- Generalization bounds: perspectives from information theory and PAC-Bayes
- Information-directed sampling for bandits: a primer
This page was built for publication: An information-theoretic analysis of Thompson sampling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2810878)
