StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer Learning

TL;DR

This paper introduces a reinforcement learning approach with curriculum transfer learning for controlling multiple units in StarCraft micromanagement, achieving high success rates and improved training efficiency.

Contribution

It proposes a novel multi-agent reinforcement learning framework with shared policies and a curriculum transfer learning method for scalable, efficient training in complex StarCraft scenarios.

Findings

100% win rate in small scenarios against built-in AI

Superior performance of curriculum transfer learning in large scenarios

Effective state representation reducing complexity

Abstract

Real-time strategy games have been an important field of game artificial intelligence in recent years. This paper presents a reinforcement learning and curriculum transfer learning method to control multiple units in StarCraft micromanagement. We define an efficient state representation, which breaks down the complexity caused by the large state space in the game environment. Then a parameter sharing multi-agent gradientdescent Sarsa({\lambda}) (PS-MAGDS) algorithm is proposed to train the units. The learning policy is shared among our units to encourage cooperative behaviors. We use a neural network as a function approximator to estimate the action-value function, and propose a reward function to help units balance their move and attack. In addition, a transfer learning method is used to extend our model to more difficult scenarios, which accelerates the training process and improves the learning performance. In small scale scenarios, our units successfully learn to combat and defeat the built-in AI with 100% win rates. In large scale scenarios, curriculum transfer learning method is used to progressively train a group of units, and shows superior performance over some baseline methods in target scenarios. With reinforcement learning and curriculum transfer learning, our units are able to learn appropriate strategies in StarCraft micromanagement scenarios.