Scholarlink

The Knowledge-Infused Policy Gradient with Upper Confidence Bound (KIPGUCB) strategy addresses contextual Multi-Armed Bandit problems by balancing exploration and exploitation. This study evaluates the performance of a KIPGUCB-based agent in the partially observable environment of StarCraft II. Unlike traditional Deep Reinforcement Learning models that rely on low-level atomic actions, our approach enhances decision-making by employing higher-level tactical strategies. A tactic manager dynamically selects optimal tactics based on game state and reward signals which improves resource management and structured tasks such as unit training. The agent’s performance is compared with a StarCraft II Grandmaster, a novice human player and DeepMind’s baseline RL agent across five mini-games. Experimental results show that the KIPGUCB-based agent outperforms the baseline model in resource-focused and structured tasks but struggles in combat-oriented scenarios requiring adaptive responses.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Assessment of the Knowledge-Infused Policy Gradient Approach for StarCraft

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Adarsh Varshney,
  • Karthick Seshadri,
  • Viswa Kiran Andraju

摘要

The Knowledge-Infused Policy Gradient with Upper Confidence Bound (KIPGUCB) strategy addresses contextual Multi-Armed Bandit problems by balancing exploration and exploitation. This study evaluates the performance of a KIPGUCB-based agent in the partially observable environment of StarCraft II. Unlike traditional Deep Reinforcement Learning models that rely on low-level atomic actions, our approach enhances decision-making by employing higher-level tactical strategies. A tactic manager dynamically selects optimal tactics based on game state and reward signals which improves resource management and structured tasks such as unit training. The agent’s performance is compared with a StarCraft II Grandmaster, a novice human player and DeepMind’s baseline RL agent across five mini-games. Experimental results show that the KIPGUCB-based agent outperforms the baseline model in resource-focused and structured tasks but struggles in combat-oriented scenarios requiring adaptive responses.