Part of Advances in Neural Information Processing Systems 35 (NeurIPS 2022) Main Conference Track
Nicholas A. Roy, Junkyung Kim, Neil Rabinowitz
Explaining the behavior of AI systems is an important problem that, in practice, is generally avoided. While the XAI community has been developing an abundance of techniques, most incur a set of costs that the wider deep learning community has been unwilling to pay in most situations. We take a pragmatic view of the issue, and define a set of desiderata that capture both the ambitions of XAI and the practical constraints of deep learning. We describe an effective way to satisfy all the desiderata: train the AI system to build a causal model of itself. We develop an instance of this solution for Deep RL agents: Causal Self-Talk. CST operates by training the agent to communicate with itself across time. We implement this method in a simulated 3D environment, and show how it enables agents to generate faithful and semantically-meaningful explanations of their own behavior. Beyond explanations, we also demonstrate that these learned models provide new ways of building semantic control interfaces to AI systems.