To alleviate traffic congestion in urban areas, electronic toll collection (ETC) systems are
deployed all over the world. Despite the merits, tolls are usually pre-determined and fixed …

We propose a reinforcement learning (RL) algorithm for generating a trading strategy in a
realistic setting, that includes transaction costs and factors driving the asset dynamics. We …

With the rapid increase of population with Alzheimer's disease, it has been more and more
costly for the society to provide personal care to the patients. Artificial intelligence (AI) …

Here I apply three reinforcement learning methods to the full, continuous action, swing-up
acrobot control benchmark problem. These include two approaches from the literature …

Reinforcement learning (RL) is a subdomain of machine learning concerned with achieving
optimal behavior by interacting with an unknown and potentially stochastic environment. The …

In this paper I investigate methods of applying reinforcement learning to continuous state-
and action-space problems without a policy function. I compare the performance of four …

Abstract We investigate Actor-Critic algorithms from the non-convex optimisation
perspective. For the past years, powerful Deep Reinforcement Learning algorithms, such as …

Dynamic Programming and a Neural Network-based value-function approximation
approach have demonstrated superior performance in solving sequential decision making …

Reinforcement learning (RL) is a subdomain of machine learning concerned with achieving
optimal behavior by interacting with an unknown and potentially stochastic environment. The …

Here the Newton's Method direct action selection approach to continuous action-space
reinforcement learning is extended to use an eligibility trace. This is then compared to the …