Improving Deep Reinforcement Learning in Minecraft with Action Advice
This addresses the challenge of high computational costs and aliasing in complex environments for reinforcement learning practitioners, though it is incremental as it builds on existing interactive machine learning techniques.
The paper tackled the problem of training deep reinforcement learning agents in visually aliased 3D environments like Minecraft by using human action advice to reduce susceptibility to aliasing, finding that methods like Feedback Arbitration and Newtonian Action Advice improved training efficiency and robustness under varying advice conditions.
Training deep reinforcement learning agents complex behaviors in 3D virtual environments requires significant computational resources. This is especially true in environments with high degrees of aliasing, where many states share nearly identical visual features. Minecraft is an exemplar of such an environment. We hypothesize that interactive machine learning IML, wherein human teachers play a direct role in training through demonstrations, critique, or action advice, may alleviate agent susceptibility to aliasing. However, interactive machine learning is only practical when the number of human interactions is limited, requiring a balance between human teacher effort and agent performance. We conduct experiments with two reinforcement learning algorithms which enable human teachers to give action advice, Feedback Arbitration and Newtonian Action Advice, under visual aliasing conditions. To assess potential cognitive load per advice type, we vary the accuracy and frequency of various human action advice techniques. Training efficiency, robustness against infrequent and inaccurate advisor input, and sensitivity to aliasing are examined.