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.
翻译:注入人类知识是加速强化学习的有效方法(RL) 。 但是,这些方法没有得到充分探讨。 本文展示了我们发现的一种发现, 一种抽象的前瞻性模型( 思维游戏( TG) ) 与转移学习( TL) 相结合是一种有效的方法。 我们把StarCraft II 当作我们的学习环境。 在设计TG的帮助下, 代理人可以在64x64 地图上学习99%的赢率, 与64x64 内建的AI 相比, 仅使用一个商业机器的1. 08小时。 我们还表明, TG 方法没有想象的那么严格。 它可以与设计大致的 TG 一起工作, 当环境变化时也可以有用。 与以前基于模型的RL 相比, 我们展示TG 更有效。 我们还提出了一个TG 假设, 赋予TG 不同忠诚水平的影响力。 对于存在不平等状态和行动空间的真正游戏, 我们提出了一个新型的 XfrNet, 其效用得到了验证, 同时实现90% 赢率 10 AI 。 我们争论TG 方法可能会在人类高效学习RL 的进一步 。