Towards Cognition-level Goal Reasoning for Playing Real-Time Strategy Games
نویسندگان
چکیده
We describe a 3-layer architecture for an automated Real-Time Strategy game player. In these kinds of games, opponent players create and manage large armies of units to defeat one another requiring strategic thinking. Players give commands asynchronously, requiring rapid thinking and reaction. Our 3-layer architecture builds on current automated players for these kinds of games, which focuses on rapid control. The first layer is the control layer that implements the standard reactive player in RTS games. The second layer is a goal reasoning mechanism; it selects goals that are executed by the control layer. The second layer reasons at the cognitive level; it introduces symbolic notions of goal and examines the outcomes of its own decisions. The third layer introduces a meta-reasoning layer that reasons strategically on long-term plans. Our ideas are grounded by using the MIDCA cognitive architecture.
منابع مشابه
Building Human-Level AI for Real-Time Strategy Games
Video games are complex simulation environments with many real-world properties that need to be addressed in order to build robust intelligence. In particular, realtime strategy games provide a multi-scale challenge which requires both deliberative and reactive reasoning processes. Experts approach this task by studying a corpus of games, building models for anticipating opponent actions, and p...
متن کاملTransfer Learning in Real-Time Strategy Games Using Hybrid CBR/RL
The goal of transfer learning is to use the knowledge acquired in a set of source tasks to improve performance in a related but previously unseen target task. In this paper, we present a multilayered architecture named CAse-Based Reinforcement Learner (CARL). It uses a novel combination of Case-Based Reasoning (CBR) and Reinforcement Learning (RL) to achieve transfer while playing against the G...
متن کاملTowards Integrating Role Playing Game Constructs in Real-Time Strategy Games
The computer game industry has grown to a million dollar industry with new titles coming out every month. However, with all these great achievements, the video game industry does have one significant problem: games are played in similar ways. One particular genre for which this is true is the group of real time strategy games. Almost all of these games have the same structure, in which players ...
متن کاملRobust Opponent Modeling in Real-Time Strategy Games using Bayesian Networks
Opponent modeling is a key challenge in Real-Time Strategy (RTS) games as the environment is adversarial in these games, and the player cannot predict the future actions of her opponent. Additionally, the environment is partially observable due to the fog of war. In this paper, we propose an opponent model which is robust to the observation noise existing due to the fog of war. In order to cope...
متن کاملAssociations Between Avid Action and Real-Time Strategy Game Play and Cognitive Performance: a Pilot Study
Over the past 15 years, numerous studies have demonstrated that action video game players outperform non-gamers on a variety of cognitive measures. However, few researchers have examined the potential beneficial effects of playing real-time strategy games or the effect of playing multiple game genres. As such, the purpose of the current study was to (a) replicate the existing findings that show...
متن کامل