Vijayaraghavan Murali — accepted AI-conference papers

2018

Neural Sketch Learning for Conditional Program Generation

Vijayaraghavan Murali, Letao Qi, Swarat Chaudhuri, Chris Jermaine

ICLR 2018oral

We study the problem of generating source code in a strongly typed, Java-like programming language, given a label (for example a set of API calls or types) carrying a small amount of information about the code that is desired. The generated programs are expected to respect a `"realistic" relationshi…

Cited by 164 Source ↗PDF ↗code ↗Scholar ↗

2018

Programmatically Interpretable Reinforcement Learning

Abhinav Verma, Vijayaraghavan Murali, Rishabh Singh, Pushmeet Kohli, Swarat Chaudhuri

ICML 2018oral

We present a reinforcement learning framework, called Programmatically Interpretable Reinforcement Learning (PIRL), that is designed to generate interpretable and verifiable agent policies. Unlike the popular Deep Reinforcement Learning (DRL) paradigm, which represents policies by neural networks, P…

Cited by 497 Source ↗PDF ↗Scholar ↗