Experiments with Encoding Structured Data for Neural Networks
This work addresses encoding structured data for AI agents in a domain-specific military wargaming context, but it appears incremental as it builds on existing MCTS and DQN methods.
The paper tackled the problem of encoding complex structured data from a Python class for neural networks in the Battlespace game-playing domain, but no concrete results or numbers were reported.
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.