arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.10290cs.AI
收藏

神经网络结构化数据编码的实验

Experiments with Encoding Structured Data for Neural Networks

Penn State University(宾夕法尼亚州立大学)

Sujay Nagesh Koujalgi, Jonathan Dodge

AI总结:

本文旨在为Battlespace博弈环境开发结合MCTS和DQN技术的AI智能体,重点探讨呈现Python类中复杂结构化数据的编码技术,作为构建智能体的必要前提。

摘要:

该项目旨在创建一个能在名为Battlespace的博弈环境中选择优质动作的AI智能体。像Battlespace这样的序列环境是规划问题的重要试验台,因此国防部使用此类环境进行兵棋推演演习。我们开发的智能体结合了蒙特卡洛树搜索(MCTS)和深度Q网络(DQN)技术,以在游戏环境中导航、避开障碍物、与对手交互并夺取旗帜。本文将重点探讨我们探索的编码技术,以呈现存储在Python类中的复杂结构化数据,这是构建智能体的必要前提。

英文摘要:

The project's aim is to create an AI agent capable of selecting good actions in a game-playing domain called Battlespace. Sequential domains like Battlespace are important testbeds for planning problems, as such, the Department of Defense uses such domains for wargaming exercises. The agents we developed combine Monte Carlo Tree Search (MCTS) and Deep Q-Network (DQN) techniques in an effort to navigate the game environment, avoid obstacles, interact with adversaries, and capture the flag. This paper will focus on the encoding techniques we explored to present complex structured data stored in a Python class, a necessary precursor to an agent.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑