Reinforcement Learning of Intelligent Characters in Fighting Action Games
نویسندگان
چکیده
Abstract. In this paper, we investigate reinforcement learning (RL) of intelligent characters, based on neural network technology, for fighting action games. RL can be either on-policy or off-policy. We apply both schemes to tabula rasa learning and adaptation. The experimental results show that (1) in tabula rasa leaning, off-policy RL outperforms on-policy RL, but (2) in adaptation, on-policy RL outperforms off-policy RL.
منابع مشابه
Comparison of AI Techniques for Fighting Action Games - Genetic Algorithms/Neural Networks/Evolutionary Neural Networks
Recently many studies have attempted to implement intelligent characters for fighting action games. They used genetic algorithms, neural networks, and evolutionary neural networks to create intelligent characters. This study quantitatively compared the performance of these three AI techniques in the same game and experimental environments, and analyzed the results of experiments. As a result, n...
متن کاملHierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents
This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...
متن کاملTowards autonomous behavior learning of non-player characters in games
Non-Player-Characters (NPCs), as found in computer games, can be modelled as intelligent systems, which serve to improve the interactivity and playability of the games. Although reinforcement learning (RL) has been a promising approach to creating the behaviour models of non-player characters (NPC), an initial stage of exploration and low performance is typically required. On the other hand, im...
متن کاملArnold: An Autonomous Agent to Play FPS Games
Advances in deep reinforcement learning have allowed autonomous agents to perform well on Atari games, often outperforming humans, using only raw pixels to make their decisions. However, most of these games take place in 2D environments that are fully observable to the agent. In this paper, we present Arnold, a completely autonomous agent to play First-Person Shooter Games using only screen pix...
متن کاملApplying Reinforcement Learning for the AI in a Tank-Battle Game
Reinforcement learning is an unsupervised machine learning method in the field of Artificial Intelligence and offers high performance in simulating the thinking ability of a human. However, it requires a trialand-error process to achieve this goal. In the research field of game AIs, it is a good approach that can give the nonplayer-characters (NPCs) in digital games more human-like qualities. I...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2006