… This paper explores using Reinforcement Learning (RL) [20] to implement more sophisticated
ways to select actions. RL is a branch of machine learning that is directly applicable in …

… AI technology discussed in this paper is a reinforcement learning algorithm named DDPG.
An in-house program named DARwind is utilized to run the dynamics response analysis of …

… In this paper, we consider the episodic reinforcement learning setting in which the agent
accesses p and r by interacting with the environment over successive episodes, ie, the agent …

In reinforcement learning (RL) research, it is common to assume access to direct online
interactions with the environment. However in many real-world applications, access to the …

… We are concerned with value-function approximation in batch-mode reinforcement
learning, which is related to and sometimes known as Approximate Dynamic Programming (ADP; …

… problem of certifying stability of reinforcement learning policies when interconnected with …
; furthermore, we analyze and establish its (non)conservatism. Empirical evaluations on two …

… In Section 4 we present a practical reinforcement learning (RL) algorithm for implementing
an SR system with an application to ad offers. In Section 5 we present an algorithm for safely …

… After introducing our approach and providing a finite-sample analysis, we empirically
evaluate REMPS on both benchmark and realistic environments by comparing our results with …

… Next, we demonstrate how to solve for the optimal attack problem in practice, and empirically
show that with the techniques from Deep Reinforcement Learning (DRL), we can find …

… Off-policy multi-step reinforcement learning algorithms consist of conservative and non…
Motivated by the empirical results and the lack of theory, we carry out theoretical analyses of Peng’…