Write, Execute, Assess: Program Synthesis with a REPL

Kevin M Ellis, Maxwell Nye, Yewen Pu, Felix Sosa, Joshua Tenenbaum, Armando Solar-Lezama

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.

Code Link: The code is provided in the supplementary materials.

CMT Num: 4927