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.

翻译：识别环境中的因果变量及其干预方式在机器人技术和具身人工智能等应用中具有核心价值。虽然智能体通常能与环境交互并可能隐式扰动某些因果变量的行为，但其影响的目标往往未知。本文证明，若智能体与因果变量的交互可通过未知二元变量描述（例如每个因果变量存在两种不同机制，如观测机制与干预机制），则在多种常见设置（如加性高斯噪声模型）下仍可识别因果变量。基于该可识别性结果，我们提出BISCUIT方法，可同步学习因果变量及其对应的二元交互变量。在三个机器人启发数据集上，BISCUIT准确识别了因果变量，并可扩展至复杂、真实的具身人工智能环境。