Neural-Symbolic Descriptive Action Model from Images: The Search for STRIPS

Not submitted to the 30th International Conference on Automated Planning and SchedulingNeural-Symbolic Descriptive Action Model from Images: The Search for STRIPS Masataro Asai MIT -IBM Watson AI Lab, Cambridge USA IBM Research Abstract Recent work on Neural-Symbolic systems that learn the discrete planning model from images has opened a promising direction for expanding the scope of Automated Planning and Scheduling to the raw, noisy data. However, previous work only partially addressed this problem, utilizing the black-box neural model as the successor generator. In this work, we propose Double-Stage Action Model Acquisition (DSAMA), a system that obtains a descriptive PDDL action model with explicit preconditions and effects over the propositional variables unsupervised-learned from images. DSAMA trains a set of Random Forest rule-based classifiers and compiles them into logical formulae in PDDL. While we obtained a competitively accurate PDDL model compared to a black-box model, we observed that the resulting PDDL is too large and complex for the state-of-the-art standard planners such as Fast Downward primarily due to the PDDL-SAS translator bottleneck. From this negative result, we show that this translator bottleneck cannot be addressed just by using a different, existing rule-based learning method, and we point to the potential future directions. 1 Introduction Recently, Latplan system (Asai and Fukunaga 2018) successfully connected a subsymbolic neural network (NN) system and a symbolic Classical Planning system to solve various visually presented puzzle domains. The system consists of four parts: 1) The State AutoEncoder (SAE) neural network learns a bidirectional mapping between images and propositional states with unsupervised training. The proposed framework opened a promising direction for applying a variety of symbolic methods to the real world -- For example, the search space generated by Latplan was shown to be compatible with a symbolic Goal Recognition system (Amado et al. 2018a; 2018b). Several variations replacing the state encoding modules have also been proposed: Causal InfoGAN (Kurutach et al. 2018) uses a GAN-based framework, First-Order SAE (Asai 2019) learns the First Order Logic symbols (instead of the propositional ones), and Zero-Suppressed SAE (Asai (:action a0:parameters ():precondition [D0]:effect (and (when [E00] (z0)) (when (not [E00]) (not (z0))) (when [E01] (z1)) (when (not [E01]) (not (z1))) ...)) Figure 1: An example DSAMA compilation result for the first action (i.e. Despite these efforts, Latplan is missing a critical feature of the traditional Classical Planning systems: The use of State-of-the-Art heuristic functions.