BISCUIT: Causal Representation Learning from Binary Interactions
This work addresses the challenge of unknown intervention targets in robotics and embodied AI, offering a novel approach for causal representation learning.
The paper tackles the problem of identifying causal variables from binary interactions in environments like robotics, showing that causal variables can be identified under common setups such as additive Gaussian noise models, and proposes BISCUIT, a method that accurately learns these variables on three robotic-inspired datasets.
Identifying the causal variables of an environment and how to intervene on them is of core value in applications such as robotics and embodied AI. While an agent can commonly interact with the environment and may implicitly perturb the behavior of some of these causal variables, often the targets it affects remain unknown. In this paper, we show that causal variables can still be identified for many common setups, e.g., additive Gaussian noise models, if the agent's interactions with a causal variable can be described by an unknown binary variable. This happens when each causal variable has two different mechanisms, e.g., an observational and an interventional one. Using this identifiability result, we propose BISCUIT, a method for simultaneously learning causal variables and their corresponding binary interaction variables. On three robotic-inspired datasets, BISCUIT accurately identifies causal variables and can even be scaled to complex, realistic environments for embodied AI.