73 papers with code • 3 benchmarks • 4 datasets
Starcraft II is a RTS game; the task is to train an agent to play the game.
( Image credit: The StarCraft Multi-Agent Challenge )
At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, where global state information is available and communication constraints are lifted.
This is often due to the belief that PPO is significantly less sample efficient than off-policy methods in multi-agent systems.
Finally, we present initial baseline results for canonical deep reinforcement learning agents applied to the StarCraft II domain.
A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible.
Both TStarBot1 and TStarBot2 are able to defeat the built-in AI agents from level 1 to level 10 in a full game (1v1 Zerg-vs-Zerg game on the AbyssalReef map), noting that level 8, level 9, and level 10 are cheating agents with unfair advantages such as full vision on the whole map and resource harvest boosting.
We propose FACtored Multi-Agent Centralised policy gradients (FACMAC), a new method for cooperative multi-agent reinforcement learning in both discrete and continuous action spaces.
Gym-$μ$RTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning
In recent years, researchers have achieved great success in applying Deep Reinforcement Learning (DRL) algorithms to Real-time Strategy (RTS) games, creating strong autonomous agents that could defeat professional players in StarCraft~II.