Independently Controllable Factors
This work addresses the challenge of representation learning for AI agents by enabling unsupervised discovery of controllable factors, which could improve interpretability and efficiency in reinforcement learning and robotics, though it is incremental as it builds on prior disentanglement frameworks.
The paper tackles the problem of learning disentangled representations by hypothesizing that some causal factors correspond to independently controllable aspects of the environment, proposing an objective function that enables an agent to discover these factors through interaction without extrinsic rewards, and experimentally verifying its effectiveness in disentangling such aspects.
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most previous work focuses on the static setting (e.g., with images), we postulate that some of the causal factors could be discovered if the learner is allowed to interact with its environment. The agent can experiment with different actions and observe their effects. More specifically, we hypothesize that some of these factors correspond to aspects of the environment which are independently controllable, i.e., that there exists a policy and a learnable feature for each such aspect of the environment, such that this policy can yield changes in that feature with minimal changes to other features that explain the statistical variations in the observed data. We propose a specific objective function to find such factors and verify experimentally that it can indeed disentangle independently controllable aspects of the environment without any extrinsic reward signal.