- Original Pdf: pdf
- TL;DR: We train a natural media painting agent using environment model. Based on our painting agent, we present a novel approach to train a constrained painting agent that follows the command encoded in the observation.
- Abstract: We present a novel approach to train a natural media painting using reinforcement learning. Given a reference image, our formulation is based on stroke-based rendering that imitates human drawing and can be learned from scratch without supervision. Our painting agent computes a sequence of actions that represent the primitive painting strokes. In order to ensure that the generated policy is predictable and controllable, we use a constrained learning method and train the painting agent using the environment model and follows the commands encoded in an observation. We have applied our approach on many benchmarks and our results demonstrate that our constrained agent can handle different painting media and different constraints in the action space to collaborate with humans or other agents.