Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning
This addresses the problem of accelerating reinforcement learning with human knowledge for complex games like StarCraft, though it appears incremental as it builds on existing model-based RL and transfer learning concepts.
The paper tackles efficient reinforcement learning in StarCraft II by using an abstract forward model (thought-game) combined with transfer learning, achieving a 99% win-rate on a 64x64 map against Level-7 AI in 1.08 hours and a 90% win-rate against Level-10 AI.
Injecting human knowledge is an effective way to accelerate reinforcement learning (RL). However, these methods are underexplored. This paper presents our discovery that an abstract forward model (thought-game (TG)) combined with transfer learning (TL) is an effective way. We take StarCraft II as our study environment. With the help of a designed TG, the agent can learn a 99% win-rate on a 64x64 map against the Level-7 built-in AI, using only 1.08 hours in a single commercial machine. We also show that the TG method is not as restrictive as it was thought to be. It can work with roughly designed TGs, and can also be useful when the environment changes. Comparing with previous model-based RL, we show TG is more effective. We also present a TG hypothesis that gives the influence of different fidelity levels of TG. For real games that have unequal state and action spaces, we proposed a novel XfrNet of which usefulness is validated while achieving a 90% win-rate against the cheating Level-10 AI. We argue that the TG method might shed light on further studies of efficient RL with human knowledge.