Learning Lifted Action Models from Unsupervised Visual Traces

ArXi:2604.19043v1 Announce Type: new Efficient construction of models capturing the preconditions and effects of actions is essential for applying AI planning in real-world domains. Extensive prior work has explored learning such models from high-level descriptions of state and/or action sequences. In this paper, we tackle a challenging setting: learning lifted action models from sequences of state images, without action observation. We propose a deep learning framework that jointly learns state prediction, action prediction, and a lifted action model. We also.