|
|
Human Guided Ensemble Learning in StarCraft Host Publication: 16th Adaptive and Learning Agents Workshop, ALA 2016 Authors: T. Verstraeten, R. Radulescu, Y. Jadoul, T. Brys, A. Harutyunyan, P. Vrancx and A. Nowé Publication Date: May. 2016 Number of Pages: 7
Abstract: In reinforcement learning, agents are typically only rewarded based on the task requirements. However, in complex environments, such reward schemes are not informative enough to efficiently learn the optimal strategy. Previous literature shows that feedback from multiple humans could be an effective and robust approach to guide the agent towards its goal. However, this feedback is often too complex to specify beforehand and is generally given during the learning process. We introduce real-time human guided ensemble learning, in which feedback from multiple advisers is learned simultaneously with the agent's behaviour. We evaluate our approach in a small scale one-on-one combat scenario in StarCraft: Brood War. Our results show that a single expert adviser can provide proper guidance, while using groups of multiple advisers does not improve the convergence speed. In future work, we will investigate an alternative to the tile-coding approximator in order to effectively incorporate advice from multiple humans. External Link.
|
|
