Interpretable (Un)Controllable Features in MDP's
Abstract: 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.
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Pascal_Poupart2
Submission Number: 1111
Loading