Synthesizing Programs for Images using Reinforced Adversarial Learning
This repository contains agents and environments described in the ICML'18 paper "Synthesizing Programs for Images using Reinforced Adversarial Learning". For the time being, we are providing two simulators: one based on libmypaint
and one based on Fluid Paint
(NOTE: our implementation is written in C++
whereas the original is in javascript
). Additionally, we supply a Sonnet module for the unconditional agent as well as pre-trained model snapshots (9 agents from a single population for libmypaint
and 1 agent for Fluid Paint
) available from TF-Hub.