PLANS: Robust Program Learning from Neurally Inferred Specifications
Recent years have seen the rise of statistical program learning based on neural models as an alternative to traditional rule-based systems for programming by example. Rule-based approaches offer correctness guarantees in an unsupervised way as they inherently capture logical rules, while neural models are more realistically scalable to raw, high-dimensional input, and provide resistance to noisy I/O specifications. We introduce PLANS (Program LeArning from Neurally inferred Specifications), a hybrid model for program synthesis from visual observations that gets the best of both worlds, relying on (i) a neural architecture trained to extract abstract, high-level information from each raw individual input (ii) a rule-based system using the extracted information as I/O specifications to synthesize a program capturing the different observations. In order to address the key challenge of making PLANS resistant to noise in the network's output, we introduce a filtering heuristic for I/O specifications based on selective classification techniques. We obtain state-of-the-art performance at program synthesis from diverse demonstration videos in the Karel and ViZDoom environments, while requiring no ground-truth program for training. We make our implementation available at github.com/rdang-nhu/PLANS.
Code (1)
Tasks
Program SynthesisSimilar Papers 제목 키워드 기반
PLANS: Neuro-Symbolic Program Learning from Videos
Recent years have seen the rise of statistical program learning based on neural models as an alternative to traditional rule-based systems for programming by example. Rule-based approaches offer correctness guarantees in…
Program SynthesisJoint Verification and Refinement of Language Models for Safety-Constrained Planning
Although pre-trained language models can generate executable plans (e.g., programmatic policies) for solving robot tasks, the generated plans may violate task-relevant logical specifications due to the models' black-box …
Language ModelingLanguage ModellingTowards Efficient Neurally-Guided Program Induction for ARC-AGI
ARC-AGI is an open-world problem domain in which the ability to generalize out-of-distribution is a crucial quality. Under the program induction paradigm, we present a series of experiments that reveal the efficiency and…
ARCProgram inductionBayesian Inference of Temporal Task Specifications from Demonstrations
When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task. Prior research into learning from de…
Bayesian InferenceProbabilistic ProgrammingContributions of natural ventilation on thermal performance of alternative floor plan designs
During the earliest phase of architectural design process, practitioners after analyzing the client's design program, legal requirements, topographic constraints, and preferences synthesize these requirements into archit…