Decision-making in the face of uncertainty is a significant challenge in machine learning,
and the multi-armed bandit model is a commonly used framework to address it. This …

Exploration in reinforcement learning (RL) suffers from the curse of dimensionality when the
state-action space is large. A common practice is to parameterize the high-dimensional …

Reinforcement learning (RL) with linear function approximation has received increasing
attention recently. However, existing work has focused on obtaining $\sqrt {T} $-type regret …

Modern tasks in reinforcement learning have large state and action spaces. To deal with
them efficiently, one often uses predefined feature mapping to represent states and actions …

Policy gradient methods are among the most effective methods for large-scale reinforcement
learning, and their empirical success has prompted several works that develop the …

We consider the variant of the stochastic multi-armed bandit problem where the stochastic
reward distributions may change abruptly several times. In contrast to previous work, we are …

We derive an algorithm that achieves the optimal (up to constants) pseudo-regret in both
adversarial and stochastic multi-armed bandits without prior knowledge of the regime and …

We derive an algorithm that achieves the optimal (within constants) pseudo-regret in both
adversarial and stochastic multi-armed bandits without prior knowledge of the regime and …

Motivated by emerging need of learning algorithms for large scale networked and
decentralized systems, we introduce a distributed version of the classical stochastic Multi …

We study the problem of constrained efficient global optimization, where both the objective
and constraints are expensive black-box functions that can be learned with Gaussian …