We describe the conception of a visualization and transformation tool for traces of the real-time strategy (RTS) computer game StarCraft. The development of our tool StarTrace is driven by the domain the traces originate from as well as the observable elements those traces contain. We elaborate on those influences, which also include both the structure of the existing game traces and the requir...

Recent work in mouse movement analysis has determined that, with sufficient data, users can be uniquely identified solely by their mouse movements. We consider the domain of video games and attempt to use mouse movements to identify game players. We conduct a user study that requires users to perform baseline tasks in a controlled environment, and then play Solitaire and StarCraft, two popular ...

Since the concepts of "customer innovation" (2002) and “crowdsourcing” (2006) were introduced, researchers have focused their attention on the phenomenon of crowdsourcing innovation. Relevant research includes the crowd’s characteristics, the crowd’s applicability in different phases of developing innovations, and instrumental aspects of web-based crowd innovation. However, there has been no re...

We consider scenarios from the real-time strategy game StarCraft as new benchmarks for reinforcement learning algorithms. We propose micromanagement tasks, which present the problem of the short-term, low-level control of army members during a battle. From a reinforcement learning point of view, these scenarios are challenging because the stateaction space is very large, and because there is no...

Goal-driven autonomy (GDA) is a conceptual model for creating an autonomous agent that monitors a set of expectations during plan execution, detects when discrepancies occur, builds explanations for the cause of failures, and formulates new goals to pursue when planning failures arise. While this framework enables the development of agents that can operate in complex and dynamic environments, i...

Offline multi-agent reinforcement learning (MARL) aims to learn effective policies from pre-collected datasets, which is an important step toward the deployment of systems in real-world applications. However, practice, each individual behavior policy that generates joint trajectories usually has a different level how well it performs. e.g., agent random while other agents are medium policies. I...

Deep reinforcement learning (DRL) has reached an unprecedent level on complex tasks like game solving (Go [], StarCraft II []), and autonomous driving. However, applications to real financial assets are still largely unexplored it remains open question whether DRL can reach super human level. In this demo, we showcase state-of-the-art methods for selecting portfolios according environment, with...

This paper presents GHOST, a combinatorial optimization framework that a Real-Time Strategy (RTS) AI developer can use to model and solve any problem encoded as a constraint satisfaction/optimization problem. We show a way to model three different problems as a constraint satisfaction/optimization problem, using instances from the RTS game StarCraft as test beds. Each problem belongs to a speci...

Standard game tree search algorithms, such as minimax or Monte Carlo Tree Search, assume the existence of an accurate forward model that simulates the effects of actions in the game. Creating such model, however, is a challenge in itself. One cause of the complexity of the task is the gap in level of abstraction between the informal specification of the model and its implementation language. To...

Real-Time Strategy (RTS) games have become an attractive domain for AI research in recent years, due to their dynamic, multi-agent and multi-objective environments. Micromanagement, a core component of many RTS games, involves the control of multiple agents to accomplish goals that require fast, real time assessment and reaction. In this paper, we present the application and evaluation of a Neu...