Experiments with Encoding Structured Data for Neural Networks

Autor:	Koujalgi, Sujay Nagesh, Dodge, Jonathan
Rok vydání:	2024
Předmět:	Computer Science - Artificial Intelligence I.2.4
Druh dokumentu:	Working Paper
Popis:	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. Comment: 18 pages, 8 figures, 2 tables
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.10290 Zobrazit plný text záznamu View this record from Arxiv