About this document
Adaptive Exploration and Temporal Attention in Reinforcement Learning For Autonomous Air Combat Decision Making by official.kashifa is a document available to read on EtoBox.
This article presents PPO-ITDS, an advanced decision-making framework for autonomous air combat using deep reinforcement learning (DRL). It addresses the limitations of existing DRL agents by integrating long-horizon strategic reasoning and enhancing tactical exploration, resulting in a 43% increase in Elo score and win rates over 70% against other algorithms. The study emphasizes the importance of bridging strategic planning and tactical execution to improve the effectiveness of unmanned combat aerial vehi
- Author
- official.kashifa
- Language
- EN