Deep reinforcement learning agents for continuous control are known to exhibit significant
instability in their performance over time. In this work, we provide a fresh perspective on …

We present a scalable and effective exploration strategy based on Thompson sampling for
reinforcement learning (RL). One of the key shortcomings of existing Thompson sampling …

Offline reinforcement learning (RL) aims to learn policies from static datasets. The value
overestimation of out-of-distribution (OOD) actions makes it difficult to directly apply general …

Deep reinforcement learning (DRL) has achieved remarkable success in diverse areas,
including gaming AI, scientific simulations, and large-scale (HPC) system scheduling. DRL …

Evolutionary Algorithms and Deep Reinforcement Learning have both successfully solved
control problems across a variety of domains. Recently, algorithms have been proposed …

Stein Variational Gradient Descent (SVGD) is a highly efficient method to sample from an
unnormalized probability distribution. However, the SVGD update relies on gradients of the …

Reinforcement learning~(RL) is a versatile framework for learning to solve complex real-
world tasks. However, influences on the learning performance of RL algorithms are often …

Training a reinforcement learning model is critical for various AI tasks. However, determining
the hardware resources required for training RL models is challenging due to the interaction …

Offline RL suffers from the distribution shift problem. One way to address this issue is to
constrain the divergence between the target policy and the behavior policy. However …

Deep reinforcement learning (DRL) has achieved remarkable success in various fields,
including gaming AI [10, 35, 65, 70], robotics [13, 78], and system scheduling [12, 45, 49, 55] …