… Deep reinforcement learning (DRL) algorithms have been successfully deployed in various
types of simulation environments, yet their success beyond simulated worlds has been …

… Hence, we use another online training method (deep reinforcement learning) based on
VISSIM in this paper. The principal is to train the decision-making model from the interaction …

… As described in Section 5 every N steps we reinitialize the simulated environment with
ground-truth data. By default we use N = 50, in some experiments we set N = 25 or N = 100. It is …

… not only different simulation environments but also different … simulation environments benefit
the most from single core performance. Yet, using a multi core system, multiple simulations …

With the recent advances in Reinforcement Learning (RL), there have been tremendous
interests in employing RL for recommender systems. However, directly training and evaluating a …

… In the following sections, we describe our proposed reinforcement learning method in detail.
… For other simulated environments, we observed similar entropy and temperature curves …

… between simulated environments and the real world; (8) large-scale … in reinforcement
learning: how can we design a more efficient reinforcement learning algorithm for an agent to learn …

… to address observation discrepancies between simulated and real-world environments or
even discrepancies between different tasks. When formalizing domain adaptation in …

… While current benchmark reinforcement learning (RL) tasks have … learning with real-world
data. By testing increasingly complex RL algorithms on lowcomplexity simulation environments…

… Abstract—We use reinforcement learning in simulation to … Using reinforcement learning
in simulation and synthetic data … the desired task in a simulated environment” and indeed, in …