Disentangled (Un)Controllable Features
Kooi, Jacob E., Hoogendoorn, Mark, François-Lavet, Vincent
–arXiv.org Artificial Intelligence
In the context of MDPs with high-dimensional states, downstream tasks are predominantly applied on a compressed, low-dimensional representation of the original input space. A variety of learning objectives have therefore been used to attain useful representations. However, these representations usually lack interpretability of the different features. We present a novel approach that is able to disentangle latent features into a controllable and an uncontrollable partition. We illustrate that the resulting partitioned representations are easily interpretable on three types of environments and show that, in a distribution of procedurally generated maze environments, it is feasible to interpretably employ a planning algorithm in the isolated controllable latent partition.
arXiv.org Artificial Intelligence
Jan-3-2024
- Country:
- Europe > Netherlands > North Holland > Amsterdam (0.05)
- Genre:
- Research Report (0.70)
- Technology: