Write, Execute, Assess: Program Synthesis with a REPL

TitleWrite, Execute, Assess: Program Synthesis with a REPL
Publication TypeConference Proceedings
Year of Publication2019
AuthorsEllis, K, Nye, M, Pu, Y, Sosa, F, Tenenabum, JB, Solar-Lezama, A
Conference NameNeural Information Processing Systems (NeurIPS 2019)
Date Published11/2019
Conference LocationVancouver, Canada
Abstract

We present a neural program synthesis approach integrating components which write, execute, and assess code to navigate the search space of possible programs. We equip the search process with an interpreter or a read-eval-print-loop (REPL), which immediately executes partially written programs, exposing their semantics. The REPL addresses a basic challenge of program synthesis: tiny changes in syntax can lead to huge changes in semantics. We train a pair of models, a policy that proposes the new piece of code to write, and a value function that assesses the prospects of the code written so-far. At test time we can combine these models with a Sequential Monte Carlo algorithm. We apply our approach to two domains: synthesizing text editing programs and inferring 2D and 3D graphics programs.

Associated Module: 

CBMM Relationship: 

  • CBMM Funded