Starcraft Micromanagement With Reinforcement Learning And Curriculum Transfer Learning

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 defea

Stats

• citations143
• S2 citations—
• github stars0
• HF likes0
• heat score16.19
• arxiv keyshao2018starcraft

Related papers

• Episodic Exploration For Deep Deterministic Policies: An Application To Starcraft Micromanagement Tasks (2016)0.00
• Macro Action Selection With Deep Reinforcement Learning In Starcraft (2018)9.92
• Starcraft II: A New Challenge For Reinforcement Learning (2017)0.00
• Applying Supervised And Reinforcement Learning Methods To Create Neural-network-based Agents For Playing Starcraft II (2021)0.00
• SCC: An Efficient Deep Reinforcement Learning Agent Mastering The Game Of Starcraft II (2020)0.00
• Transformer-based Value Function Decomposition For Cooperative Multi-agent Reinforcement Learning In Starcraft (2022)8.82
• Efficient Reinforcement Learning For Starcraft By Abstract Forward Models And Transfer Learning (2019)8.60
• Growing Action Spaces (2019)0.00