Real-Time Strategy (RTS) tasks involve training an agent to play video games with continuous gameplay and high-level macro-strategic goals such as map control, economic superiority and more.
( Image credit: Multi-platform Version of StarCraft: Brood War in a Docker Container )
Stratega, a general strategy games framework, has been designed to foster research on computational intelligence for strategy games.
In this paper, we survey the progress of DRL methods, including value-based, policy gradient, and model-based algorithms, and compare their main techniques and properties.
We consider the problem of high-level strategy selection in the adversarial setting of real-time strategy games from a reinforcement learning perspective, where taking an action corresponds to switching to the respective strategy.
We believe that our results indicate the usefulness of potential fields as a representation, and of evolutionary multi-objective optimization as an approach, for generating good micro.
Games with large branching factors pose a significant challenge for game tree search algorithms.
The network is then used to select a script --- an abstract action --- to produce low level actions for all units.