Game-independent AI agents for playing Atari 2600 console games
Game-independent AI agents for playing Atari 2600 console games
复制标题
用于玩 Atari 2600 主机游戏的独立于游戏的 AI 代理
DOI：
--
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
Yavar Naddaf
中科院分区：
文献类型：
--
作者：
Yavar Naddaf
这项研究重点是开发播放任意Atari 2600游戏机游戏的AI代理，而没有任何游戏规定的假设或先验知识。游戏屏幕和控制台RAM学习玩给定的游戏。对未来的行动，仅探索一小部分状态空间来确保我们方法的通用性，一旦使用四个特定的游戏来确保我们的方法的通用性。选择是完整的，在50个随机选择的游戏中，对代理的性能进行了评估。性能是通过基于搜索的方法实现的。
This research focuses on developing AI agents that play arbitrary Atari 2600 console games without having any game-specific assumptions or prior knowledge. Two main approaches are considered: reinforcement learning based methods and search based methods. The RL-based methods use feature vectors generated from the game screen as well as the console RAM to learn to play a given game. The search-based methods use the emulator to simulate the consequence of actions into the future, aiming to play as well as possible by only exploring a very small fraction of the state-space. To insure the generic nature of our methods, all agents are designed and tuned using four specific games. Once the development and parameter selection is complete, the performance of the agents is evaluated on a set of 50 randomly selected games. Significant learning is reported for the RL-based methods on most games. Additionally, some instances of human-level performance is achieved by the search-based methods.