Imitation learning is a powerful family of techniques for learning
sensorimotor coordination in immersive environments. We apply imitation
learning to attain state-of-the-art performance on hard exploration problems in
the Minecraft environment. We report experiments that highlight the influence
of network architecture, loss function, and data augmentation. An early version
of our approach reached second place in the MineRL competition at NeurIPS 2019.
Here we report stronger results that can be used as a starting point for future
competition entries and related research. Our code is available at
this https URL

本研究将模仿学习应用于 Minecraft 环境中的探索问题，通过实验调研了网络结构、损失函数和数据扩充等因素的影响，并取得了良好的表现，可以作为未来竞赛和相关研究的起点。

在 Minecraft 中实现模仿学习的扩展

Scaling Imitation Learning in Minecraft

During interaction with others, we perceive and produce social actions in
close temporal distance or even simultaneously. It has been argued that the
motor system is involved in perception and action, playing a fundamental role
in the handling of actions produced by oneself and by others. But how does it
distinguish in this processing between self and other, thus contributing to
self-other distinction? In this paper we propose a hierarchical model of
sensorimotor coordination based on principles of perception-action coupling and
predictive processing in which self-other distinction arises during action and
perception. For this we draw on mechanisms assumed for the integration of cues
for a sense of agency, i.e., the sense that an action is self-generated. We
report results from simulations of different scenarios, showing that the model
is not only able to minimize free energy during perception and action, but also
showing that the model can correctly attribute sense of agency to own actions.

本文提出了一个基于感知 - 动作耦合和预测处理原则的层级传感器运动协调模型，该模型能够在感知和动作过程中实现自我和他人的区分，并且具有正确地将代理感归因于自己动作的能力。