Intelligent agents can learn to represent the action spaces of other agents
simply by observing them act. Such representations help agents quickly learn to
predict the effects of their own actions on the environment and to plan complex
action sequences. In this work, we address the problem of learning an agent's
action space purely from visual observation. We use stochastic video prediction
to learn a latent variable that captures the scene's dynamics while being
minimally sensitive to the scene's static content. We introduce a loss term
that encourages the network to capture the composability of visual sequences
and show that it leads to representations that disentangle the structure of
actions. We call the full model with composable action representations
Composable Learned Action Space Predictor (CLASP). We show the applicability of
our method to synthetic settings and its potential to capture action spaces in
complex, realistic visual settings. When used in a semi-supervised setting, our
learned representations perform comparably to existing fully supervised methods
on tasks such as action-conditioned video prediction and planning in the
learned action space, while requiring orders of magnitude fewer action labels.
Project website: this https URL

本研究使用随机视频预测学习了捕捉场景动态的潜在变量，同时尽量不受场景内容的影响，从而学习代理的行动空间；该方法在半监督学习下表现相当于现有的完全监督方法，在任务如行动条件视频预测和计划学习行动空间时，需要几个数量级更少的行动标签。