论文标题
利用语言说明用于可解释和组成的增强学习
Exploiting Language Instructions for Interpretable and Compositional Reinforcement Learning
论文作者
论文摘要
在这项工作中，我们提出了一种通过使用诊断分类器来制作代理组成的替代方法。由于需要在自动决策过程中进行可解释的代理，因此我们试图从RL代理中解释潜在空间，以在复杂的语言教学中确定其目前的目标。结果表明，分类过程会导致隐藏状态的变化，从而使它们更容易解释，但也会导致零射击性能转移到新指令。最后，我们限制了分类的监督信号，并观察到类似但不太明显的效果。
In this work, we present an alternative approach to making an agent compositional through the use of a diagnostic classifier. Because of the need for explainable agents in automated decision processes, we attempt to interpret the latent space from an RL agent to identify its current objective in a complex language instruction. Results show that the classification process causes changes in the hidden states which makes them more easily interpretable, but also causes a shift in zero-shot performance to novel instructions. Lastly, we limit the supervisory signal on the classification, and observe a similar but less notable effect.
