Deep learning frameworks have often focused on either usability or speed, but not both.
PyTorch is a machine learning library that shows that these two goals are in fact compatible …

Many real-world applications require artificial agents to compete and coordinate with other
agents in complex environments. As a step** stone to this goal, the domain of StarCraft …

Opponent modeling is the ability to use prior knowledge and observations in order to predict
the behavior of an opponent. This survey presents a comprehensive overview of existing …

Injecting human knowledge is an effective way to accelerate reinforcement learning (RL).
However, these methods are underexplored. This article presents our discovery that an …

Contract bridge is a competitive-cooperative multiplayer game. In the bidding phase, the
decision-making process is complex, given the extensive range of inaccessible information …

Unsupervised visual representation learning offers the opportunity to leverage large corpora
of unlabeled trajectories to form useful visual representations, which can benefit the training …

In contested environments, self-exploration is a self-* property that serves as a proactive
mechanism for countering threats posed by adversaries. Specifically, self-exploration …

Real-time strategy games often times mimic the appearance and feel of military-like
command and control systems. Artificial intelligence and machine learning research enjoys …

Game AI is of great importance as games are simulations of reality. Recent research on
game AI has shown much progress in various kinds of games, such as console games …

Contract bridge is a multi-player imperfectinformation game where one partnership
collaborate with each other to compete against the other partnership. The game consists of …