3 problems

Thompson-sampling conjecture. A Thompson-sampling-based algorithm may also work for the contextual dueling bandit setting because its stochastic nature encourages the agent to expl…

Consider stabilizable multidimensional linear quadratic regulator systems, and let Thompson Sampling (TS) denote an adaptive control strategy that samples a model from a posterior…

In a logistic bandit, the link function is … where $\beta\in(0,\infty)$ is fixed and known. For each $t=1,2,\ldots$, let $\t{\theta}^*_t$ and $\t{\theta}_t$ satisfy the conditions…