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. |
Year | Venue | DocType |
---|---|---|
2019 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019) | Journal |
Volume | ISSN | Citations |
32 | 1049-5258 | 3 |
PageRank | References | Authors |
0.38 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kevin Ellis | 1 | 58 | 7.09 |
Maxwell Nye | 2 | 5 | 2.43 |
Yewen Pu | 3 | 55 | 6.47 |
Felix Sosa | 4 | 3 | 1.39 |
Joshua B. Tenenbaum | 5 | 4445 | 437.33 |
Armando Solar-Lezama | 6 | 791 | 59.48 |