Training Agent for First-person Shooter Game with Actor-critic Curriculum Learning
نویسندگان
چکیده
In this paper, we propose a new framework for training vision-based agent for First-Person Shooter (FPS) Game, in particular Doom. Our framework combines the state-of-the-art reinforcement learning approach (Asynchronous Advantage Actor-Critic (A3C) model [Mnih et al. (2016)]) with curriculum learning. Our model is simple in design and only uses game states from the AI side, rather than using opponents’ information [Lample & Chaplot (2016)]. On a known map, our agent won 10 out of the 11 attended games and the champion of Track1 in ViZDoom AI Competition 2016 by a large margin, 35% higher score than the second place.
منابع مشابه
Learning to Play Donkey Kong Using Neural Networks and Reinforcement Learning
Neural networks and reinforcement learning have successfully been applied to various games, such as Ms. Pacman and Go. We combine multilayer perceptrons and a class of reinforcement learning algorithms known as actor-critic to learn to play the arcade classic Donkey Kong. Two neural networks are used in this study: the actor and the critic. The actor learns to select the best action given the g...
متن کاملGame Designers Training First Person Shooter Bots
Interactive training is well suited to computer games as it allows game designers to interact with otherwise autonomous learning algorithms. This paper investigates the outcome of a group of five commercial first person shooter game designers using a custom built interactive training tool to train first person shooter bots. The designers are asked to train a bot using the tool, and then comment...
متن کاملSimulation Experience Design Methods for Training the Forces to Think Adaptively
The present paper discusses the Simulation Experience Design Method employed to create engaging learning environments for training U.S. Armed Forces to think adaptively. This design method is based on the notion that one’s total experience in the simulated environment, or crucible, is integral to the learning process. A “crucible” experience is a defining moment that unleashes abilities, forces...
متن کاملLearning to be a Bot: Reinforcement Learning in Shooter Games
This paper demonstrates the applicability of reinforcement learning for first person shooter bot artificial intelligence. Reinforcement learning is a machine learning technique where an agent learns a problem through interaction with the environment. The Sarsa( ) algorithm will be applied to a first person shooter bot controller to learn the tasks of (1) navigation and item collection, and (2) ...
متن کاملCreating Human-like Autonomous Players in Real-time First Person Shooter Computer Games
This paper illustrates how we create a software agent by employing FALCON, a self-organizing neural network that performs reinforcement learning, to play a well-known first person shooter computer game known as Unreal Tournament 2004. Through interacting with the game environment and its opponents, our agent learns in real-time without any human intervention. Our agent bot participated in the 2...
متن کامل