Offline reinforcement learning (RL) presents a promising approach for learning reinforced
policies from offline datasets without the need for costly or unsafe interactions with the …

We focus on parameterized policy search for reinforcement learning over continuous action
spaces. Typically, one assumes the score function associated with a policy is bounded …

Stochastic gradient descent is a classic algorithm that has gained great popularity especially
in the last decades as the most common approach for training models in machine learning …

Reinforcement learning is a framework for interactive decision-making with incentives
sequentially revealed across time without a system dynamics model. Due to its scaling to …

Recent empirical evidence indicates that many machine learning applications involve heavy-
tailed gradient noise, which challenges the standard assumptions of bounded variance in …

We present a novel approach to improve the performance of deep reinforcement learning
(DRL) based outdoor robot navigation systems. Most, existing DRL methods are based on …

We consider the task of heavy-tailed statistical estimation given streaming $ p $-dimensional
samples. This could also be viewed as stochastic optimization under heavy-tailed …

As one of the most important and influential algorithms in reinforcement learning, the
Proximal Policy Optimization (PPO) algorithm has demonstrated outstanding performance …

In online reinforcement learning, operators predict the return by weighting the successors'
estimated value. However, due to the lack of uncertainty quantification, weights assigned by …

Some common assumptions when building machine learning pipeline are:(1) the training
data is sufficiently “clean” and well-behaved, so that there are few or no outliers, or that the …