Causal Transfer for Imitation Learning and Decision Making under Sensor-shift
This addresses sensor-shift issues in imitation learning and decision-making, offering incremental improvements for AI agents in robotics or autonomous systems.
The paper tackles the problem of learning from demonstrations when there are differences in sensory inputs between demonstrators, observers, and agents, proposing a causal model-based framework for transfer learning under sensor-shifts. It validates methods on simulated and semi-real data, providing theoretical bounds on proxy solutions.
Learning from demonstrations (LfD) is an efficient paradigm to train AI agents. But major issues arise when there are differences between (a) the demonstrator's own sensory input, (b) our sensors that observe the demonstrator and (c) the sensory input of the agent we train. In this paper, we propose a causal model-based framework for transfer learning under such "sensor-shifts", for two common LfD tasks: (1) inferring the effect of the demonstrator's actions and (2) imitation learning. First we rigorously analyze, on the population-level, to what extent the relevant underlying mechanisms (the action effects and the demonstrator policy) can be identified and transferred from the available observations together with prior knowledge of sensor characteristics. And we device an algorithm to infer these mechanisms. Then we introduce several proxy methods which are easier to calculate, estimate from finite data and interpret than the exact solutions, alongside theoretical bounds on their closeness to the exact ones. We validate our two main methods on simulated and semi-real world data.