Reinforcement learning agents providing advice in complex video games
نویسندگان
چکیده
This article introduces a teacher-student framework for reinforcement learning, synthesizing and extending material that appeared in conference proceedings [22] and in a non-archival workshop paper [6]. In this framework, a teacher agent instructs a student agent by suggesting actions the student should take as it learns. However, the teacher may only give such advice a limited number of times. We present several novel algorithms that teachers can use to budget their advice effectively, and we evaluate them in two complex video games: StarCraft and Pac-Man. Our results show that the same amount of advice, given at different moments, can have different effects on student learning, and that teachers can significantly affect student learning even when students use different learning methods and state representations.
منابع مشابه
Giving Advice about Preferred Actions to Reinforcement Learners Via Knowledge-Based Kernel Regression
We present a novel formulation for providing advice to a reinforcement learner that employs supportvector regression as its function approximator. Our new method extends a recent advice-giving technique, called Knowledge-Based Kernel Regression (KBKR), that accepts advice concerning a single action of a reinforcement learner. In KBKR, users can say that in some set of states, an action’s value ...
متن کاملCreating Intelligent Agents in Games
Game playing has long been a central topic in artificial intelligence. Whereas early research focused on utilizing search and logic in board games, machine learning in video games is driving much of the recent research. In video games, intelligent behavior can be naturally captured through interaction with the environment, and biologically inspired techniques such as evolutionary computation, n...
متن کاملFuzzy Q-learning for First Person Shooters
Here machine learning techniques in the context of their application within computer games is examined. The scope of the study was that of reinforcement learning [RL] algorithms as applied to the control of enemies in a video game dynamic environment thus providing interesting new experiences for different game players. The project proved reinforcement learning algorithms are suitable and usefu...
متن کاملDeep Reinforcement Learning of Video Games
The ability to learn is arguably the most crucial aspect of human intelligence. In reinforcement learning, we attempt to formalize a certain type of learning that is based on rewards and penalties. These supervisory signals should guide an agent to learn optimal behavior. In particular, this research focuses on deep reinforcement learning, where the agent should learn to play video games solely...
متن کاملGenerating Real-Time Crowd Advice to Improve Reinforcement Learning Agents
Reinforcement learning is a powerful machine learning paradigm that allows agents to autonomously learn to maximize a scalar reward. However, it often suffers from poor initial performance and long learning times. This paper discusses how collecting on-line human feedback, both in real time and post hoc, can potentially improve the performance of such learning systems. We use the game Pac-Man t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Connect. Sci.
دوره 26 شماره
صفحات -
تاریخ انتشار 2014